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

    Neuronpedia

    INDEX
    Explanations

    past tense forms of verbs and their relationships to subjects and objects

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

    preceding possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    pronoun or determiner follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lma
    -0.45
    glClear
    -0.44
    ھو
    -0.42
    tula
    -0.41
    soever
    -0.41
    ื่น
    -0.40
    作
    -0.40
    IRT
    -0.40
    fiques
    -0.39
    msford
    -0.39
    POSITIVE LOGITS
     the
    1.13
     another
    0.92
     our
    0.92
     one
    0.91
     what
    0.84
     where
    0.83
     ciò
    0.81
     yksi
    0.81
     démocr
    0.77
     your
    0.73
    Act Density 0.601%

    No Known Activations