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

    Neuronpedia

    INDEX
    Explanations

    Time calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ment
    -0.07
     quat
    -0.07
    ██
    -0.07
     domic
    -0.07
     Hend
    -0.06
     west
    -0.06
     マ
    -0.06
     Additionally
    -0.06
     tar
    -0.06
    Dave
    -0.06
    POSITIVE LOGITS
     compromising
    0.07
     순간
    0.07
    riet
    0.06
    (tid
    0.06
    .flow
    0.06
    ifying
    0.06
    alien
    0.06
     Recursive
    0.06
    ład
    0.06
    ATRIX
    0.06
    Act Density 0.001%

    No Known Activations