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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clip
    -0.07
    udicots
    -0.07
    ，而
    -0.07
    rieg
    -0.06
     targeting
    -0.06
    rypton
    -0.06
     deutschland
    -0.06
    opus
    -0.06
     Cri
    -0.06
    zoek
    -0.06
    POSITIVE LOGITS
    utures
    0.06
     permits
    0.06
    ecurity
    0.06
     mesma
    0.06
    su
    0.06
    owanie
    0.06
    /react
    0.06
    eways
    0.06
    ЮЛ
    0.06
    efs
    0.06
    Act Density 0.027%

    No Known Activations