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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bonus
    -0.08
     키
    -0.07
     Narc
    -0.07
    .kafka
    -0.07
    �ng
    -0.07
    看着
    -0.07
    letics
    -0.07
    普通
    -0.07
    _CTRL
    -0.07
     쓰
    -0.07
    POSITIVE LOGITS
     eş
    0.07
    elease
    0.06
     rehe
    0.06
     transcript
    0.06
     occurred
    0.06
     rhe
    0.06
     textbook
    0.06
     conex
    0.06
    _rev
    0.06
     overview
    0.06
    Act Density 0.000%

    No Known Activations