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

    Neuronpedia

    INDEX
    Explanations

    programming and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     understandable
    -0.08
     cooper
    -0.07
    (Convert
    -0.07
     flags
    -0.07
     gating
    -0.07
    fore
    -0.06
     realiz
    -0.06
     kill
    -0.06
     Engines
    -0.06
    conduct
    -0.06
    POSITIVE LOGITS
    (withIdentifier
    0.07
     PUB
    0.07
    ",&
    0.07
    .Parent
    0.06
    oot
    0.06
     postId
    0.06
    .tencent
    0.06
    ）：
    0.06
     addSubview
    0.06
    、『
    0.06
    Act Density 0.302%

    No Known Activations