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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Valid
    -0.07
    906
    -0.07
     disclosure
    -0.06
     slik
    -0.06
     Marc
    -0.06
    _indices
    -0.06
     Azure
    -0.06
    904
    -0.06
     Dana
    -0.06
    μος
    -0.06
    POSITIVE LOGITS
    駅
    0.07
     getSession
    0.07
    asonic
    0.06
    iphers
    0.06
    سم
    0.06
     органи
    0.06
     mutlu
    0.06
    、私
    0.06
    /stats
    0.06
     Pause
    0.06
    Act Density 0.022%

    No Known Activations