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

    Neuronpedia

    INDEX
    Explanations

    statements expressing doubt or uncertainty

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

    Follows a comma or "I", often conditions

    np_acts-logits-general · gemini-2.0-flash

    I followed by specific verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dacă
    -0.68
    if
    -0.66
     if
    -0.65
    若是
    -0.57
     IF
    -0.57
    若
    -0.56
     若
    -0.55
    If
    -0.54
     если
    -0.54
    rax
    -0.53
    POSITIVE LOGITS
     ujednoznacz
    0.69
     Италијани
    0.66
    MLLoader
    0.62
     then
    0.61
    رشف
    0.56
     estekak
    0.56
    ########.
    0.53
     AssemblyCulture
    0.52
    тельств
    0.52
    Према
    0.52
    Act Density 0.203%

    No Known Activations