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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey expectations or beliefs about the nature of things

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

    forms of 'to be' and 'should'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jugé
    -0.39
    śle
    -0.37
     hidratante
    -0.37
     trattano
    -0.36
    ाहरण
    -0.35
     monstruo
    -0.35
     liker
    -0.35
    windowFixed
    -0.34
     disad
    -0.34
     ſeveral
    -0.33
    POSITIVE LOGITS
    providedIn
    0.51
    phosa
    0.49
    GraphicsUnit
    0.48
    GHIJKLM
    0.47
    دانشنامهٔ
    0.47
    IVITY
    0.46
    IndentedString
    0.43
     المعيارى
    0.43
    epam
    0.43
    VersionUID
    0.43
    Act Density 0.031%

    No Known Activations