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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or excitement

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

    conversational interjections and acknowledgements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.39
    曖昧さ回避
    -0.35
     Protección
    -0.35
     rembour
    -0.35
    qtype
    -0.35
     quæ
    -0.33
    entibus
    -0.33
     décid
    -0.32
    bitField
    -0.31
     apresenta
    -0.31
    POSITIVE LOGITS
     kaarangay
    0.59
    caras
    0.48
    ArgsConstructor
    0.47
     OMITBAD
    0.47
    tembro
    0.46
    majánló
    0.46
    othelioma
    0.45
    anners
    0.45
    ROIT
    0.45
     Rueda
    0.44
    Act Density 0.067%

    No Known Activations