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

    Neuronpedia

    INDEX
    Explanations

    collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -hooks
    -0.07
     confiscated
    -0.07
    itou
    -0.07
    ops
    -0.07
     ocup
    -0.07
    ende
    -0.06
     calling
    -0.06
    _org
    -0.06
    OPS
    -0.06
    -mort
    -0.06
    POSITIVE LOGITS
     McMaster
    0.07
     네이트온
    0.07
    娜
    0.06
    inement
    0.06
    ันออก
    0.06
    к
    0.06
    阅读次数
    0.06
     Scatter
    0.06
     Daily
    0.06
    Ctrls
    0.06
    Act Density 0.593%

    No Known Activations