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

    Neuronpedia

    INDEX
    Explanations

    capitalized strings inside computer code, particularly Java

    oai_token-act-pair · gemini-2.0-flash

    Software code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.52
     betweenstory
    -0.52
    gen
    -0.47
    spot
    -0.45
     ipsum
    -0.44
    genos
    -0.44
     espon
    -0.43
     af
    -0.43
     Flags
    -0.43
    弁
    -0.43
    POSITIVE LOGITS
     houſe
    0.69
     greateſt
    0.65
     purpoſe
    0.64
     ſtate
    0.63
     beſt
    0.61
    Rhestr
    0.61
    tedì
    0.61
     Majefty
    0.61
     quæ
    0.59
     ſte
    0.59
    Act Density 0.170%

    No Known Activations