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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations of concepts or processes

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

    definition of a term or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.50
     verzorg
    -0.47
    новниш
    -0.41
     Taktlose
    -0.41
    DMETHOD
    -0.40
    antMatchers
    -0.40
    Dearest
    -0.39
    AutoresizingMask
    -0.37
    atecas
    -0.36
    ſche
    -0.35
    POSITIVE LOGITS
     phenomenon
    0.54
     phénomène
    0.54
     term
    0.49
     fenô
    0.47
     phenomena
    0.46
     fenomeno
    0.45
     Begriff
    0.43
    astify
    0.43
     процесс
    0.42
     phénomènes
    0.42
    Act Density 0.214%

    No Known Activations