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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    monių
    -0.70
     propOrder
    -0.65
    PerformLayout
    -0.63
    ServiceModel
    -0.63
     Untold
    -0.63
    Owned
    -0.62
    Offering
    -0.60
    Way
    -0.59
    Decided
    -0.59
    Producing
    -0.59
    POSITIVE LOGITS
    but
    0.39
    up
    0.39
    on
    0.37
    not
    0.37
    and
    0.36
    to
    0.36
    of
    0.35
    or
    0.35
    time
    0.35
    imp
    0.34
    Act Density 0.486%

    No Known Activations