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

    Neuronpedia

    INDEX
    Explanations

    symbols and indicators of features or functions

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

    symbols followed by specific words or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.73
     Infórmanos
    -0.59
     rowspan
    -0.58
    tvguidetime
    -0.58
     المعيارى
    -0.57
    afficheront
    -0.56
     nahilalakip
    -0.55
     colspan
    -0.54
    balleur
    -0.52
    ритори
    -0.52
    POSITIVE LOGITS
    ◆◇
    0.59
    ➩
    0.57
    ︎
    0.57
     contextLoads
    0.56
    ("%.
    0.55
     handleClick
    0.54
     jLabel
    0.52
    ◆◆
    0.51
    ➋
    0.50
    ☸
    0.49
    Act Density 0.020%

    No Known Activations