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

    Neuronpedia

    INDEX
    Explanations

    critical infrastructure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avy
    -0.07
    𫸩
    -0.07
     possessed
    -0.07
     его
    -0.07
    agenta
    -0.07
    xxx
    -0.06
    ôle
    -0.06
     dg
    -0.06
     Young
    -0.06
    🔅
    -0.06
    POSITIVE LOGITS
    .Est
    0.07
    -application
    0.07
    气候变化
    0.07
    _ENDIAN
    0.07
    urity
    0.07
    \Storage
    0.07
    _else
    0.07
    全年
    0.06
    .localScale
    0.06
    	sql
    0.06
    Act Density 0.059%

    No Known Activations