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

    Neuronpedia

    INDEX
    Explanations

    phrases that explain causation or reasoning starting with "because."

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

    just because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supervivencia
    -0.38
    ValueStyle
    -0.37
     porém
    -0.34
     natomiast
    -0.33
     Zustimmung
    -0.33
     Internasional
    -0.30
    ongi
    -0.30
     already
    -0.30
     canais
    -0.29
     الرياضيه
    -0.28
    POSITIVE LOGITS
    Autoritní
    0.88
    msgTypes
    0.78
    pushFollow
    0.75
    GEBURTSDATUM
    0.72
     esternos
    0.70
    CppCodeGen
    0.70
    oredCriteria
    0.68
    makeText
    0.66
    SharedDtor
    0.66
    SequentialGroup
    0.63
    Act Density 0.081%

    No Known Activations