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

    Neuronpedia

    INDEX
    Explanations

    terms related to specialized functions and processes

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

    actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bacio
    -0.41
     betweenstory
    -0.38
     Abonnez
    -0.35
     typelib
    -0.35
     Inscrivez
    -0.34
     propOrder
    -0.33
     türlü
    -0.32
     conhece
    -0.32
     saiba
    -0.31
     Serviço
    -0.30
    POSITIVE LOGITS
     CURIAM
    0.80
     kasarigan
    0.78
     ब्रेकडाउन
    0.63
     consultato
    0.57
     سكانية
    0.55
    URLException
    0.54
    ArgumentParser
    0.54
     podjela
    0.54
    extAlignment
    0.53
    lapia
    0.53
    Act Density 0.077%

    No Known Activations