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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or preference

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

    asking for wants or needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.52
    ніципалі
    -0.45
     Govern
    -0.45
    ⓧ
    -0.44
    MessageTagHelper
    -0.43
    ulage
    -0.42
    englanniksi
    -0.42
    ậc
    -0.40
    󠁣
    -0.40
    Mait
    -0.40
    POSITIVE LOGITS
     propOrder
    0.46
    IntoConstraints
    0.44
     MainAxisSize
    0.38
    edit
    0.37
     libremente
    0.37
    Autoritní
    0.37
    LabelTagHelper
    0.34
     prefeitura
    0.34
     persa
    0.34
     retenir
    0.34
    Act Density 0.014%

    No Known Activations