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

    Neuronpedia

    INDEX
    Explanations

    person names and scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ruim
    -0.81
    arrón
    -0.78
    polizei
    -0.77
     zij
    -0.77
    digt
    -0.76
    eras
    -0.75
    atikan
    -0.73
     Historical
    -0.73
    ăng
    -0.72
    quila
    -0.72
    POSITIVE LOGITS
     adapted
    0.94
     string
    0.88
    hese
    0.77
     estimated
    0.77
     estudar
    0.76
     estudia
    0.76
     updateUser
    0.75
     adapting
    0.75
     senseless
    0.74
     cờ
    0.73
    Act Density 0.000%

    No Known Activations