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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ”.↵↵
    -0.07
     zboží
    -0.07
    NT
    -0.07
    day
    -0.07
    sharing
    -0.06
     Kaf
    -0.06
     ﾞ
    -0.06
     dolaş
    -0.06
     scant
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    iggs
    0.06
     namespaces
    0.06
    기준
    0.06
    �
    0.06
     sophistication
    0.06
    /Linux
    0.06
    崇
    0.06
    _infos
    0.06
    irling
    0.06
    _NONE
    0.06
    Act Density 0.039%

    No Known Activations