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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conseguido
    -0.08
     regime
    -0.07
     plaatsvinden
    -0.07
    Extras
    -0.07
     LIN
    -0.07
    _Command
    -0.07
     ನರ
    -0.07
     ಮೂಲಕ
    -0.07
    _option
    -0.07
    -0.07
    POSITIVE LOGITS
     Uint
    0.08
    uggish
    0.07
     Uw
    0.07
    Uw
    0.07
    .big
    0.07
    UCH
    0.07
    asty
    0.07
     Adventure
    0.07
     Carvalho
    0.07
    SHOT
    0.07
    Act Density 0.001%
    No Known Activations