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

    Neuronpedia

    INDEX
    Explanations

    face and honor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hab
    0.61
    :
    0.60
    Sud
    0.59
     проис
    0.57
    Nach
    0.56
    Even
    0.55
    Mild
    0.55
    urization
    0.55
    Mat
    0.54
    H
    0.54
    POSITIVE LOGITS
    ước
    0.63
     ссылка
    0.61
     处理
    0.60
     pilha
    0.59
     lettura
    0.57
     dignidad
    0.57
    u
    0.57
    㞒
    0.56
     leitura
    0.55
    ătă
    0.55
    Act Density 0.005%

    No Known Activations