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

    Neuronpedia

    INDEX
    Explanations

    the word "can" and legal references such as "candidate", "herein", and bracketed text.

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -2.42
     can
    -1.63
    can
    -1.36
    Can
    -1.23
     Can
    -1.21
     CAN
    -0.99
    CAN
    -0.90
     could
    -0.88
     lahko
    -0.75
     may
    -0.73
    POSITIVE LOGITS
    interopRequire
    0.57
    醐
    0.55
     Ponto
    0.54
     binoculars
    0.54
    EndInit
    0.53
     Tất
    0.52
    ariana
    0.52
     Spine
    0.52
    zade
    0.51
    atase
    0.51
    Act Density 1.880%

    No Known Activations