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

    Neuronpedia

    INDEX
    Explanations

    Skirt

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rue
    0.63
     economical
    0.61
    ็จ
    0.61
     Berlín
    0.57
    ッグ
    0.56
     budgetary
    0.56
     phosphoric
    0.56
    ENSIVE
    0.56
    tements
    0.55
    çin
    0.55
    POSITIVE LOGITS
    呗
    0.63
    スマホ
    0.61
    superclass
    0.61
    cred
    0.58
    aml
    0.54
    ສະ
    0.54
    ssr
    0.54
     grandchild
    0.54
    imsu
    0.54
    authUser
    0.54
    Act Density 0.002%

    No Known Activations