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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RS
    -0.06
    Probe
    -0.06
     structs
    -0.06
    getService
    -0.06
     Quad
    -0.06
    _ABORT
    -0.06
    �
    -0.06
     carbs
    -0.06
    スレ
    -0.06
    Grand
    -0.06
    POSITIVE LOGITS
    (Yii
    0.07
     πραγμα
    0.07
    issenschaft
    0.07
     рік
    0.07
    увався
    0.07
    }@
    0.07
     zih
    0.07
     زمین
    0.06
    /k
    0.06
    .mybatisplus
    0.06
    Act Density 0.001%

    No Known Activations