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

    Neuronpedia

    INDEX
    Explanations

    **do good deeds**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Чем
    0.84
    ácil
    0.82
    Usuario
    0.81
     Само
    0.80
    abhave
    0.80
    iftoire
    0.80
    ān
    0.79
    ócio
    0.79
    älj
    0.79
     Уда
    0.79
    POSITIVE LOGITS
     peny
    0.69
     cos
    0.68
     tiga
    0.67
     seng
    0.67
    .
    0.66
     meny
    0.66
     mor
    0.65
     lots
    0.64
     g
    0.64
     and
    0.63
    Act Density 0.004%

    No Known Activations