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

    Neuronpedia

    INDEX
    Explanations

    the prefix "fore", usually indicating something that comes before

    oai_token-act-pair · gemini-2.0-flash

    fore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recul
    -0.56
     dry
    -0.55
    LLocation
    -0.49
    MigrationBuilder
    -0.48
     big
    -0.48
    ORATION
    -0.47
    นาน
    -0.47
    wój
    -0.47
    ıldız
    -0.46
    SourceChecksum
    -0.46
    POSITIVE LOGITS
    octanol
    0.61
     Waray
    0.60
     ModelExpression
    0.60
     CreateTagHelper
    0.57
    CodedInputStream
    0.56
    stdc
    0.54
     {}));
    0.54
    styleType
    0.52
     endwhile
    0.51
     سما
    0.51
    Act Density 0.458%

    No Known Activations