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

    Neuronpedia

    INDEX
    Explanations

    Inequalities and chemical notation. Method number 1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paul
    -0.07
    Paul
    -0.06
     Вік
    -0.06
     당시
    -0.06
    افظ
    -0.06
    Targets
    -0.06
    _post
    -0.06
    821
    -0.06
     CONF
    -0.06
    _SAMPLE
    -0.06
    POSITIVE LOGITS
    uated
    0.07
    ups
    0.07
    _cos
    0.06
    مم
    0.06
    ized
    0.06
    juries
    0.06
    éd
    0.06
    reet
    0.06
     Jersey
    0.06
    GEST
    0.06
    Act Density 0.033%

    No Known Activations