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

    Neuronpedia

    INDEX
    Explanations

    metal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uuid
    -0.07
     bson
    -0.07
     Canonical
    -0.06
     Kirst
    -0.06
    _Zero
    -0.06
    ]],
    -0.06
     liken
    -0.06
    欧
    -0.06
     paranoia
    -0.06
     Kawasaki
    -0.06
    POSITIVE LOGITS
    高度
    0.07
    scope
    0.07
     البلد
    0.07
    mutation
    0.06
    모
    0.06
    ۵۰
    0.06
    spd
    0.06
    apeutic
    0.06
    왔다
    0.06
    )")
    0.06
    Act Density 0.001%

    No Known Activations