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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hyper
    -0.07
     fik
    -0.07
    Perl
    -0.06
    níků
    -0.06
    (parameters
    -0.06
     funeral
    -0.06
     دلیل
    -0.06
    _ARR
    -0.06
    Norm
    -0.06
    .Photo
    -0.06
    POSITIVE LOGITS
    .es
    0.07
     компании
    0.07
     Chemistry
    0.07
    .poi
    0.06
    	↵	↵	↵	↵
    0.06
    LOCITY
    0.06
    ion
    0.06
    ("")
    0.06
     الخامسة
    0.06
    ி�
    0.06
    Act Density 0.000%

    No Known Activations