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

    Neuronpedia

    INDEX
    Explanations

    perform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hugs
    -0.07
     synonym
    -0.07
    (users
    -0.07
     ks
    -0.06
     cob
    -0.06
    уля
    -0.06
    ces
    -0.06
    zd
    -0.06
    比較
    -0.06
    ↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    General
    0.07
     directives
    0.07
     tournaments
    0.07
     insecure
    0.06
    checking
    0.06
    نجليزية
    0.06
    まり
    0.06
     attention
    0.06
    _relu
    0.06
    ��
    0.06
    Act Density 0.001%

    No Known Activations