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

    Neuronpedia

    INDEX
    Explanations

    legal rulings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appealed
    -0.07
     CLAIM
    -0.07
     creepy
    -0.07
    Inject
    -0.07
     Seç
    -0.07
     steep
    -0.06
     VIS
    -0.06
     Dre
    -0.06
     Waterproof
    -0.06
    ằ
    -0.06
    POSITIVE LOGITS
    inqu
    0.07
    (getString
    0.06
    >L
    0.06
    _ret
    0.06
    ürk
    0.06
     extremes
    0.06
    Bluetooth
    0.06
    -bel
    0.06
    ecake
    0.05
    _<
    0.05
    Act Density 0.066%

    No Known Activations