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

    Neuronpedia

    INDEX
    Explanations

    Dallas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Newton
    -0.07
    ейн
    -0.07
    'я
    -0.07
    Thai
    -0.06
    煙
    -0.06
    Martin
    -0.06
    _multiply
    -0.06
     riots
    -0.06
     **************************************************************************
    -0.06
     cg
    -0.06
    POSITIVE LOGITS
     â
    0.07
     다음
    0.06
     Liter
    0.06
    \F
    0.06
    .useState
    0.06
    .IsDBNull
    0.06
    bond
    0.06
     Virginia
    0.06
     Redskins
    0.06
    (hw
    0.06
    Act Density 0.014%

    No Known Activations