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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Voice
    -0.08
    .*;↵↵
    -0.07
     affinity
    -0.07
    -editor
    -0.07
    _inverse
    -0.07
    /rand
    -0.07
    .crm
    -0.07
    ulan
    -0.07
     DP
    -0.07
     loyal
    -0.07
    POSITIVE LOGITS
    (kind
    0.07
    ecd
    0.07
     cakes
    0.07
    izza
    0.07
     pard
    0.06
    aksi
    0.06
     licz
    0.06
     hers
    0.06
    前三
    0.06
    爹
    0.06
    Act Density 0.011%

    No Known Activations