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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     среди
    -0.07
    .logo
    -0.07
     (_)
    -0.06
     mView
    -0.06
     Bei
    -0.06
     intermedi
    -0.06
    *)↵↵
    -0.06
     Range
    -0.06
     desktop
    -0.06
    .bad
    -0.06
    POSITIVE LOGITS
     Warranty
    0.07
    either
    0.06
    ILLS
    0.06
     janvier
    0.06
    {\
    0.06
     coined
    0.06
    陣
    0.06
    PEnd
    0.06
    慶
    0.06
     tern
    0.06
    Act Density 0.009%

    No Known Activations