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

    Neuronpedia

    INDEX
    Explanations

    code snippets, paths, and version numbers

    oai_token-act-pair · gemini-2.0-flash

    code/file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addContainerGap
    -1.02
    /******/
    -0.98
     '.';
    -0.90
     يتيمه
    -0.90
    原始内容存档于
    -0.88
    . 
    -0.87
    '].'
    -0.85
     pinulongan
    -0.85
    <sup>
    -0.84
    ']['
    -0.84
    POSITIVE LOGITS
     raiſ
    0.44
    intenance
    0.44
     Efq
    0.41
     crdi
    0.41
    INTENANCE
    0.41
    ſelves
    0.41
     fevere
    0.40
     chofe
    0.40
    eterangan
    0.39
    struzioni
    0.38
    Act Density 40.525%

    No Known Activations