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

    Neuronpedia

    INDEX
    Explanations

    terms related to a predefined user profile or account setup

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

    default, error, rest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.34
     linkovi
    -1.16
    pecabe
    -1.11
     Савезне
    -1.07
     Administrativna
    -1.03
    ьаж
    -1.03
     שוליים
    -1.02
    󠁴
    -1.02
    Tembelea
    -1.02
     pinulongan
    -1.01
    POSITIVE LOGITS
     de
    0.36
     la
    0.32
     pres
    0.29
     por
    0.27
     se
    0.27
     «
    0.26
    longrightarrow
    0.26
     di
    0.25
     les
    0.25
     con
    0.25
    Act Density 0.001%

    No Known Activations