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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -feature
    -0.07
    _passed
    -0.07
    вин
    -0.06
    etration
    -0.06
    Phase
    -0.06
    면적
    -0.06
    502
    -0.06
     //////////////////////////////////////////////////////////////////////////
    -0.06
    -path
    -0.06
    pdo
    -0.06
    POSITIVE LOGITS
     rocking
    0.08
     Kurdish
    0.07
     student
    0.07
    …
    0.06
     Storm
    0.06
    _ZONE
    0.06
     mtx
    0.06
     System
    0.06
     ↑
    0.06
     listing
    0.06
    Act Density 0.001%

    No Known Activations