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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that ask for evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    crum
    0.80
    cour
    0.80
    কর
    0.77
    чан
    0.77
    cit
    0.73
    زة
    0.73
    dung
    0.71
    iot
    0.71
    عرف
    0.71
    います
    0.69
    POSITIVE LOGITS
     supersede
    0.80
     fermion
    0.79
     paquetes
    0.79
     balón
    0.77
     Darüber
    0.77
     Novos
    0.75
     miscarriage
    0.74
     vilket
    0.72
    嬷
    0.72
    وسف
    0.71
    Act Density 0.001%

    No Known Activations