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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Monad
    -0.07
     doanh
    -0.07
    nas
    -0.07
    ToBounds
    -0.06
     Au
    -0.06
     Dave
    -0.06
     ấm
    -0.06
     zn
    -0.06
    ’autres
    -0.06
     मद
    -0.06
    POSITIVE LOGITS
    charging
    0.07
    lescope
    0.07
     olmadığını
    0.06
    Verifier
    0.06
     detailing
    0.06
    iliki
    0.06
    igits
    0.06
    finding
    0.06
     japon
    0.06
    ufacturer
    0.06
    Act Density 0.000%

    No Known Activations