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

    Neuronpedia

    INDEX
    Explanations

    Related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Та
    -0.06
    ��이터
    -0.06
    楼
    -0.06
     zcela
    -0.06
     transporte
    -0.06
    _pb
    -0.06
    隊
    -0.06
    .wr
    -0.06
    ीएस
    -0.06
    _PRED
    -0.06
    POSITIVE LOGITS
     aplic
    0.07
     javax
    0.07
     Nolan
    0.07
    腐
    0.06
    appl
    0.06
    (土
    0.06
    ovah
    0.06
    	Il
    0.06
     King
    0.06
    vanized
    0.06
    Act Density 0.003%

    No Known Activations