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

    Neuronpedia

    INDEX
    Explanations

    .B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vancouver
    -0.07
     کنم
    -0.07
    札
    -0.06
    lj
    -0.06
    서관
    -0.06
     pkt
    -0.06
     OSS
    -0.06
     unprotected
    -0.06
    ΩΝ
    -0.06
    386
    -0.05
    POSITIVE LOGITS
     사진
    0.07
    _RESULT
    0.07
    اما
    0.07
    _ELEM
    0.06
     radios
    0.06
    edir
    0.06
     assumption
    0.06
     confident
    0.06
    орм
    0.06
     Peace
    0.06
    Act Density 0.003%

    No Known Activations