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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "(
    -0.07
     THIS
    -0.07
    $$$
    -0.07
     trailing
    -0.07
    (dec
    -0.07
    ailing
    -0.07
    "↵↵↵↵
    -0.07
     teh
    -0.07
     משת
    -0.06
    akra
    -0.06
    POSITIVE LOGITS
    踪
    0.07
     прием
    0.07
     Unblock
    0.07
    intérêt
    0.07
    岨
    0.06
    /backend
    0.06
    Finance
    0.06
    nement
    0.06
    _related
    0.06
    andum
    0.06
    Act Density 0.074%

    No Known Activations