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

    Neuronpedia

    INDEX
    Explanations

    code snippets that include conditional returns

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -0.66
    IntoConstraints
    -0.63
    rungsseite
    -0.60
    tvguidetime
    -0.59
     OBO
    -0.57
     Houſe
    -0.56
    -------
    -0.55
    Kontrola
    -0.54
     Chom
    -0.54
     altrett
    -0.54
    POSITIVE LOGITS
    <bos>
    1.11
    parametrize
    0.66
    mogorov
    0.55
    binant
    0.55
     veau
    0.55
     referrerpolicy
    0.53
    стероид
    0.52
    bParam
    0.50
    ridor
    0.50
    tected
    0.48
    Act Density 0.254%

    No Known Activations