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

    Neuronpedia

    INDEX
    Explanations

    phrases or structures involving parentheses and related contextual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, formulas, or technical identifiers

    np_acts-logits-general · gemini-2.0-flash

    (feel) sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بوابة
    -0.65
    PerformLayout
    -0.64
     ExecuteAsync
    -0.57
     leetcode
    -0.53
    lecteur
    -0.51
     Lec
    -0.51
    posedge
    -0.49
    lecture
    -0.49
    principalTable
    -0.49
     Octave
    -0.49
    POSITIVE LOGITS
    am
    0.87
    om
    0.86
    um
    0.85
    em
    0.79
    ams
    0.79
    ums
    0.75
    amma
    0.75
    cm
    0.74
    umm
    0.72
    OM
    0.72
    Act Density 0.387%

    No Known Activations