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

    Neuronpedia

    INDEX
    Explanations

    DataExchange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rad
    -0.06
     rover
    -0.06
    Dir
    -0.06
    740
    -0.06
     Kır
    -0.06
    Shield
    -0.06
    ``↵
    -0.06
    .cont
    -0.06
     jailed
    -0.05
     wt
    -0.05
    POSITIVE LOGITS
    DataExchange
    0.08
     eski
    0.07
    UBLISH
    0.07
     parach
    0.06
     Ultra
    0.06
     draws
    0.06
     мік
    0.06
     �
    0.06
    ois
    0.06
    archives
    0.06
    Act Density 0.000%

    No Known Activations