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

    Neuronpedia

    INDEX
    Explanations

    legal terminology, actions, and arguments.

    oai_token-act-pair · gemini-2.0-flash

    actions, arguments or statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puissiez
    -0.60
     diri
    -0.55
    انجليز
    -0.51
    sidemargin
    -0.50
    iastes
    -0.50
    erski
    -0.49
    verifyException
    -0.49
     Cue
    -0.48
    CopyWith
    -0.47
     Aquarium
    -0.47
    POSITIVE LOGITS
    <bos>
    0.75
    Autoritní
    0.71
     purpoſe
    0.71
     pleaſure
    0.68
    ContentAsync
    0.67
    rungsseite
    0.64
     myſelf
    0.62
     juſ
    0.61
     ſtate
    0.60
     Theſe
    0.60
    Act Density 19.657%

    No Known Activations