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

    Neuronpedia

    INDEX
    Explanations

    the presence of numeric values and their contextual significance

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

    Followed by numbers or special characters

    np_acts-logits-general · gemini-2.0-flash

    data packet http requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bø
    -0.40
     ModelExpression
    -0.40
    COUVER
    -0.39
     Flock
    -0.38
    座
    -0.36
     macetas
    -0.36
     nød
    -0.35
     tør
    -0.35
    CAPS
    -0.34
     nø
    -0.34
    POSITIVE LOGITS
     resourceCulture
    0.91
    httphttps
    0.57
    endpush
    0.57
     myſelf
    0.53
    WriteLiteral
    0.52
     noDo
    0.49
    OGND
    0.49
     leſs
    0.46
     vent
    0.45
     raiſ
    0.43
    Act Density 0.068%

    No Known Activations