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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谑
    -0.07
     Replies
    -0.07
     Art
    -0.07
    usk
    -0.07
     Davidson
    -0.06
    vertime
    -0.06
     adaptive
    -0.06
     Lud
    -0.06
    urniture
    -0.06
     snap
    -0.06
    POSITIVE LOGITS
    _secret
    0.07
    煟
    0.07
    crate
    0.07
     karşıs
    0.07
    ?>↵
    0.07
    available
    0.07
     وعلى
    0.07
    Density
    0.07
     חשבון
    0.06
     rides
    0.06
    Act Density 0.007%

    No Known Activations