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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    under
    -0.07
    hlen
    -0.07
     range
    -0.06
    Auf
    -0.06
    /views
    -0.06
    )}↵↵
    -0.06
    .logical
    -0.06
    몴
    -0.06
    .localStorage
    -0.06
    摏
    -0.06
    POSITIVE LOGITS
     Fucking
    0.07
     Qué
    0.07
    网络游戏
    0.07
     Martha
    0.07
     Costa
    0.07
    滥
    0.07
     anni
    0.07
     Homo
    0.07
    IVAL
    0.07
    يا
    0.07
    Act Density 0.098%

    No Known Activations