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

    Neuronpedia

    INDEX
    Explanations

    words expressing positive evaluations or descriptions

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

    positive quality or comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UIControlState
    -0.46
     saurait
    -0.44
     belleza
    -0.40
     estudantes
    -0.40
     prisonniers
    -0.40
     meille
    -0.40
     varandra
    -0.38
     avances
    -0.38
     mercancías
    -0.38
     pouvant
    -0.37
    POSITIVE LOGITS
    ConstraintMaker
    0.59
     had
    0.57
    /*++
    0.54
    xase
    0.53
     have
    0.52
     ddelweddau
    0.51
    BagLayout
    0.49
    ondissement
    0.49
    OrWhiteSpace
    0.49
    目
    0.48
    Act Density 0.014%

    No Known Activations