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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and components of mechanical systems

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

    Preceding numbers or technical terms

    np_acts-logits-general · gemini-2.0-flash

    numbers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onOptions
    -0.57
    новниш
    -0.56
     eventdata
    -0.52
     ModelExpression
    -0.51
    spots
    -0.47
     betweenstory
    -0.47
     estekak
    -0.46
     Exactos
    -0.46
    TargetException
    -0.46
     gynhyrchwyd
    -0.46
    POSITIVE LOGITS
     surla
    0.36
     Pfund
    0.34
     prawda
    0.34
     Picchu
    0.31
     kalite
    0.31
     mejores
    0.30
    pseud
    0.30
    izacji
    0.30
     SafeMath
    0.30
    发表于
    0.29
    Act Density 0.445%

    No Known Activations