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

    Neuronpedia

    INDEX
    Explanations

    actions or effects related to physical harm or change

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

    by, as, in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marca
    -0.35
    раздо
    -0.35
     responded
    -0.35
    応
    -0.34
     blanks
    -0.33
     Respond
    -0.33
    領
    -0.32
    Rea
    -0.32
    领
    -0.32
    영어
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.68
     Roskov
    0.62
    delwed
    0.46
    CppMethod
    0.45
    Abraços
    0.45
    spoiler
    0.45
    flashdata
    0.44
    ulement
    0.43
    urlopen
    0.43
     estekak
    0.42
    Act Density 0.171%

    No Known Activations