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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -team
    -0.07
    aaa
    -0.07
    '+
    -0.07
    iling
    -0.07
     Arsenal
    -0.07
    apesh
    -0.07
     renaming
    -0.07
     Sistem
    -0.07
     determination
    -0.06
    。。↵↵
    -0.06
    POSITIVE LOGITS
     подаль
    0.07
    ávací
    0.06
     avoiding
    0.06
     qp
    0.06
     uintptr
    0.06
    readOnly
    0.06
     hinted
    0.06
     ढ
    0.06
     CONDITION
    0.06
     マ
    0.06
    Act Density 0.002%

    No Known Activations