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

    Neuronpedia

    INDEX
    Explanations

    manip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zombie
    -0.08
    抵御
    -0.08
     dew
    -0.07
    .list
    -0.07
    ADMIN
    -0.07
     yü
    -0.07
    比べ
    -0.07
    �
    -0.07
     burning
    -0.07
    ерж
    -0.07
    POSITIVE LOGITS
     manipulating
    0.07
    صحف
    0.07
     translated
    0.07
    comma
    0.07
     `(
    0.07
    _equalTo
    0.07
     nv
    0.07
    Ordered
    0.07
    なる
    0.06
    adora
    0.06
    Act Density 0.010%

    No Known Activations