Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical data and approximations in the context of statistics or research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding an estimate or approximation

    np_acts-logits-general · gemini-2.0-flash

    approximations and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jährige
    -0.71
     Numerade
    -0.55
    etheless
    -0.51
    ագրություններ
    -0.51
    AutoScaleMode
    -0.50
    "");
    -0.49
    orini
    -0.49
    ,))
    -0.48
    "])
    -0.48
    ool
    -0.48
    POSITIVE LOGITS
     midway
    0.83
     halfway
    0.80
     roughly
    0.71
     ungefär
    0.68
     approxim
    0.68
     dozen
    0.68
     approximated
    0.67
     aproximado
    0.64
     equidist
    0.64
    half
    0.64
    Act Density 0.213%

    No Known Activations