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

    Neuronpedia

    INDEX
    Explanations

    regular expression syntax

    oai_token-act-pair · gemini-2.0-flash

    regular expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     >=",
    -0.67
    enterOuterAlt
    -0.65
     UIAlert
    -0.63
    migrationBuilder
    -0.61
    COUVER
    -0.61
    Rhestr
    -0.58
    awaiter
    -0.58
    Filmografie
    -0.56
    Ārējās
    -0.55
    Policy
    -0.55
    POSITIVE LOGITS
    <bos>
    0.62
     alive
    0.60
     Parcelable
    0.53
     humans
    0.52
     living
    0.51
    poids
    0.48
    alive
    0.48
    Länge
    0.48
     entities
    0.47
    Alive
    0.45
    Act Density 2.826%

    No Known Activations