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

    Neuronpedia

    INDEX
    Explanations

    phrases containing significant quotes or high-impact statements

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

    calling something a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.47
    Referências
    -0.44
    ormais
    -0.39
     lẫn
    -0.39
     pracow
    -0.38
     rayon
    -0.37
     thấm
    -0.36
    érial
    -0.35
    CloseOperation
    -0.35
     puis
    -0.34
    POSITIVE LOGITS
     CALLED
    0.62
     Called
    0.62
    Called
    0.59
    call
    0.58
     chiam
    0.56
     called
    0.56
    AndEndTag
    0.56
     call
    0.54
    calls
    0.54
     calls
    0.53
    Act Density 0.031%

    No Known Activations