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

    Neuronpedia

    INDEX
    Explanations

    ES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mov
    -0.09
    ndern
    -0.07
    Ext
    -0.07
    distribution
    -0.07
    חודש
    -0.06
     bonding
    -0.06
     ob
    -0.06
    MMC
    -0.06
    ,q
    -0.06
     месяцев
    -0.06
    POSITIVE LOGITS
    .RELATED
    0.07
    喀
    0.07
    (Token
    0.07
    ution
    0.07
    كتروني
    0.07
    _CRITICAL
    0.07
    ikt
    0.07
    eka
    0.07
    若い
    0.06
     Ug
    0.06
    Act Density 0.013%

    No Known Activations