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

    Neuronpedia

    INDEX
    Explanations

    physical objects or materials related to safety and utility

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

    worn on body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zor
    -0.35
    uzu
    -0.34
     Reinhold
    -0.33
    UNDA
    -0.33
     has
    -0.32
     Senat
    -0.32
     Wray
    -0.32
    写真は
    -0.32
    ->_
    -0.31
    mbito
    -0.31
    POSITIVE LOGITS
     transfieras
    0.67
     surla
    0.66
    setVerticalGroup
    0.65
     nakalista
    0.59
    DockStyle
    0.58
     يتيمه
    0.56
     lenker
    0.56
    OGND
    0.55
    Бахар
    0.53
    //
    0.53
    Act Density 0.021%

    No Known Activations