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

    Neuronpedia

    INDEX
    Explanations

    regular expression syntax including escape characters and character sets

    oai_token-act-pair · gemini-2.0-flash

    backslash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.82
    OGND
    -0.82
    amaño
    -0.80
    üyük
    -0.79
    VERTISEMENT
    -0.75
    ientras
    -0.71
    ceptre
    -0.71
    EndInit
    -0.70
    iaomi
    -0.70
     fathoms
    -0.70
    POSITIVE LOGITS
     //
    0.57
    /
    0.57
    //-->
    0.57
     or
    0.54
    ár
    0.53
    </strong>
    0.51
     
    0.50
    al
    0.50
    or
    0.50
     /
    0.48
    Act Density 6.419%

    No Known Activations