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

    Neuronpedia

    INDEX
    Explanations

    declarations, types, and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    warnings
    0.77
    muestra
    0.75
     windy
    0.75
    Charset
    0.74
     zeigen
    0.74
    㸸
    0.72
    Strings
    0.72
    倶
    0.72
    䒾
    0.71
     Navidad
    0.69
    POSITIVE LOGITS
    ritual
    0.74
    oyed
    0.68
     complicated
    0.66
    iffe
    0.65
    ラボ
    0.65
     injunctive
    0.65
     tang
    0.64
     conditional
    0.64
     linear
    0.64
    ham
    0.64
    Act Density 0.105%

    No Known Activations