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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dec
    -0.07
    Fixed
    -0.07
    ương
    -0.06
    Consult
    -0.06
    웃
    -0.06
     GM
    -0.06
     nause
    -0.06
     dropout
    -0.06
    Vertices
    -0.06
    .Listen
    -0.06
    POSITIVE LOGITS
     reclaimed
    0.07
    _HERE
    0.06
     conception
    0.06
     Workflow
    0.06
    自動
    0.06
     Economics
    0.06
    OPTION
    0.06
    емых
    0.06
    禁
    0.06
    /cpp
    0.06
    Act Density 0.042%

    No Known Activations