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

    Neuronpedia

    INDEX
    Explanations

    .W

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (compact
    -0.07
    립니다
    -0.07
    Pipeline
    -0.07
     plais
    -0.06
    realm
    -0.06
     tailor
    -0.06
     используется
    -0.06
    Miss
    -0.06
     Virtual
    -0.06
     borne
    -0.06
    POSITIVE LOGITS
     Searching
    0.06
    .Il
    0.06
    [curr
    0.06
    -now
    0.06
    _FAILURE
    0.05
    .NET
    0.05
     rew
    0.05
     villains
    0.05
    usch
    0.05
    .changed
    0.05
    Act Density 0.001%

    No Known Activations