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

    Neuronpedia

    INDEX
    Explanations

    quantitative and numerical representations

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

    Fractions involving "half"

    np_acts-logits-general · gemini-2.0-flash

    and a half

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.72
     الحره
    -0.64
     onAnimation
    -0.62
    oubliez
    -0.57
    ostom
    -0.56
    Portail
    -0.53
    /***/
    -0.51
    PositiveButton
    -0.49
     ExecuteAsync
    -0.49
    extAlignment
    -0.49
    POSITIVE LOGITS
     half
    1.86
    half
    1.74
    Half
    1.62
     ½
    1.61
     Half
    1.58
    ½
    1.51
     HALF
    1.44
    HALF
    1.42
    半
    1.41
     setengah
    1.34
    Act Density 0.732%

    No Known Activations