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

    Neuronpedia

    INDEX
    Explanations

    Contrasting statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    将会
    -0.07
     comics
    -0.07
     SqlConnection
    -0.07
    шиб
    -0.07
    -powered
    -0.07
    会不会
    -0.07
     assessing
    -0.07
     yeah
    -0.07
    钩
    -0.06
    -button
    -0.06
    POSITIVE LOGITS
    =target
    0.07
    مضي
    0.07
     flipped
    0.07
    璟
    0.07
    腑
    0.06
    を見て
    0.06
    יפ
    0.06
    禄
    0.06
    世俗
    0.06
    (table
    0.06
    Act Density 0.201%

    No Known Activations