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

    Neuronpedia

    INDEX
    Explanations

    mounted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kindle
    -0.08
    �
    -0.07
    _UNLOCK
    -0.07
    -disable
    -0.07
    ]--;↵
    -0.07
     fart
    -0.07
    ℠
    -0.06
     проч
    -0.06
    larınızı
    -0.06
     complain
    -0.06
    POSITIVE LOGITS
    按规定
    0.07
    atest
    0.07
     hidden
    0.07
     Goat
    0.07
    oid
    0.06
    sid
    0.06
    sections
    0.06
    td
    0.06
    PD
    0.06
    يرا
    0.06
    Act Density 0.064%

    No Known Activations