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

    Neuronpedia

    INDEX
    Explanations

    the contraction "it's", and also recognizes other short auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    letter "s"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xffffffff
    -0.74
     Normdatei
    -0.73
    ?
    -0.71
    UserScript
    -0.66
     pinulongan
    -0.66
    .}~\
    -0.64
    xffffff
    -0.63
    UPI
    -0.63
    DOCTYPE
    -0.63
    EndContext
    -0.63
    POSITIVE LOGITS
    <bos>
    1.82
    '
    0.70
    ’
    0.54
    So
    0.49
    2
    0.46
    //
    0.45
    The
    0.43
     poursuite
    0.41
     his
    0.40
     Infórmanos
    0.40
    Act Density 0.440%

    No Known Activations