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

    Neuronpedia

    INDEX
    Explanations

    adoption news anywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Year
    0.45
    _
    0.44
    incón
    0.43
     ব্য
    0.43
    ス
    0.42
    ARR
    0.41
    ari
    0.41
    name
    0.40
    ori
    0.40
    ಲ್ಲ
    0.40
    POSITIVE LOGITS
     criaturas
    0.49
     Corolle
    0.49
     Cria
    0.48
     traffic
    0.46
     criando
    0.46
     promove
    0.45
     gebruik
    0.45
     clings
    0.44
     serves
    0.44
     Мне
    0.43
    Act Density 0.005%

    No Known Activations