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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    思考
    -0.07
    ่าร
    -0.06
    個人
    -0.06
    odic
    -0.06
    �
    -0.06
    ierarchical
    -0.06
    drv
    -0.06
     unintention
    -0.06
    iyas
    -0.06
    wire
    -0.06
    POSITIVE LOGITS
    views
    0.07
     spokesman
    0.06
    _HTTP
    0.06
     Shemale
    0.06
     kat
    0.06
     epochs
    0.06
     Fancy
    0.06
    .Env
    0.06
     Gives
    0.06
    २
    0.06
    Act Density 0.000%

    No Known Activations