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

    Neuronpedia

    INDEX
    Explanations

    powerful computers, calculations

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     treated
    -0.07
     spiele
    -0.07
    IMUM
    -0.07
     Windows
    -0.07
     airport
    -0.07
    ישה
    -0.07
    只能说
    -0.07
    وض
    -0.07
    嘴
    -0.07
     condições
    -0.07
    POSITIVE LOGITS
    ##_
    0.07
    ࿙
    0.07
     Tribal
    0.07
    .onError
    0.07
     lượt
    0.07
    alink
    0.07
    Ctr
    0.06
    /*
↵
    0.06
    🏆
    0.06
    あげ
    0.06
    Act Density 0.195%

    No Known Activations