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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discs
    -0.07
     RNG
    -0.07
     Grove
    -0.07
     entrar
    -0.06
     tackles
    -0.06
     GD
    -0.06
     boolean
    -0.06
     Ψ
    -0.06
    opath
    -0.06
     adlandır
    -0.06
    POSITIVE LOGITS
     ','.
    0.07
    engin
    0.06
    _pro
    0.06
    ACLE
    0.06
     customerId
    0.06
     veterin
    0.06
    이며
    0.06
    сон
    0.06
    REN
    0.06
    澳
    0.06
    Act Density 0.290%

    No Known Activations