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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пять
    -0.07
     обо
    -0.07
     cow
    -0.07
     Ста
    -0.06
    enery
    -0.06
    _students
    -0.06
     Bonnie
    -0.06
     freshly
    -0.06
     quo
    -0.06
    itals
    -0.06
    POSITIVE LOGITS
    ‐‐
    0.07
    ��
    0.07
    sterreich
    0.07
    jí
    0.06
    GIN
    0.06
     oscill
    0.06
    .Kind
    0.06
     अख
    0.06
     Launch
    0.06
    ;//
    0.06
    Act Density 0.006%

    No Known Activations