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

    Neuronpedia

    INDEX
    Explanations

    the word "working" usually followed by a hyphen or "class"

    oai_token-act-pair · gemini-2.0-flash

    working

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.98
    writeFieldEnd
    -0.69
    Cyfeiriadau
    -0.63
    ExtendWith
    -0.57
    enumi
    -0.57
     gyhoeddwyd
    -0.56
     ligiloj
    -0.56
     NSCoder
    -0.55
    hagic
    -0.51
    GIVEREF
    -0.51
    POSITIVE LOGITS
    tispiece
    0.53
     مرئيه
    0.53
    ible
    0.49
    ientôt
    0.49
    zegor
    0.49
    pond
    0.48
     Sucre
    0.45
     XNUMX
    0.45
    $"
    0.44
    <>());
    0.44
    Act Density 0.183%

    No Known Activations