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

    Neuronpedia

    INDEX
    Explanations

    Records and information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engagement
    -0.08
     we
    -0.07
     rap
    -0.07
     @
    -0.07
     SHOW
    -0.06
     ']
    -0.06
    Computed
    -0.06
     folder
    -0.06
     Ты
    -0.06
    ienen
    -0.06
    POSITIVE LOGITS
    ่ละ
    0.06
    狂
    0.06
    newInstance
    0.06
     вип
    0.06
    Об
    0.06
     лиш
    0.06
     Pussy
    0.05
    .NewReader
    0.05
    quential
    0.05
    (point
    0.05
    Act Density 0.021%

    No Known Activations