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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SCO
    -0.08
     IPP
    -0.07
     До
    -0.07
     Joanna
    -0.07
     predecess
    -0.07
    给自己
    -0.07
    _OCCURRED
    -0.07
    برشلونة
    -0.07
    总额
    -0.06
    承担
    -0.06
    POSITIVE LOGITS
    Push
    0.08
     Guys
    0.07
     RP
    0.07
     readings
    0.07
    ܚ
    0.07
     hunters
    0.07
    Game
    0.07
    Guy
    0.06
    Parm
    0.06
    焕发
    0.06
    Act Density 0.236%

    No Known Activations