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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    获批
    -0.07
     grips
    -0.07
     uno
    -0.07
     Paris
    -0.07
    DOWNLOAD
    -0.07
    .outer
    -0.06
    اخل
    -0.06
    ABCDE
    -0.06
    _REPLACE
    -0.06
     ulcer
    -0.06
    POSITIVE LOGITS
    .java
    0.07
    _support
    0.07
    ;
↵
    0.07
     Holy
    0.06
    ervoir
    0.06
     shown
    0.06
    参数
    0.06
    cmc
    0.06
     П
    0.06
     Context
    0.06
    Act Density 0.000%

    No Known Activations