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

    Neuronpedia

    INDEX
    Explanations

    quantitative indicators of comparison among groups

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

    Relative pronouns after prepositions

    np_acts-logits-general · gemini-2.0-flash

    of whom or which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    -0.77
    EntityFramework
    -0.62
    Abitanti
    -0.60
     that
    -0.58
    from
    -0.57
    those
    -0.56
    EditorBrowsable
    -0.53
    another
    -0.52
    baomidou
    -0.51
    That
    -0.49
    POSITIVE LOGITS
     whom
    1.79
     Whom
    1.34
    whom
    1.30
    Whom
    1.07
     whence
    0.95
     quale
    0.92
    quels
    0.87
     whome
    0.87
     duquel
    0.83
     hvem
    0.81
    Act Density 0.125%

    No Known Activations