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

    Neuronpedia

    INDEX
    Explanations

    references to scales or measurements related to assessment

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

    ert scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Freuden
    -0.50
     Schwä
    -0.47
    kissen
    -0.46
     McCon
    -0.46
     Bradshaw
    -0.42
     duiz
    -0.42
     Kraus
    -0.41
     Wilcox
    -0.40
     McLeod
    -0.39
    iPad
    -0.39
    POSITIVE LOGITS
    ert
    2.86
    ERT
    2.22
    erts
    1.68
    erte
    1.46
    ERTS
    1.30
     ert
    1.29
    erta
    1.27
    ertes
    1.16
    ertal
    1.11
    erted
    1.09
    Act Density 0.010%

    No Known Activations