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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jav
    -0.06
    -buy
    -0.06
    ,name
    -0.06
    uja
    -0.06
    NetMessage
    -0.06
    Page
    -0.06
    _BLOCKS
    -0.06
    gom
    -0.06
    ename
    -0.06
    dsp
    -0.06
    POSITIVE LOGITS
    0.07
     (!$
    0.06
    “How
    0.06
    ेब
    0.06
     mirror
    0.06
     виг
    0.06
     lashes
    0.06
    ting
    0.06
    cısı
    0.06
     분
    0.06
    Act Density 0.017%

    No Known Activations