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

    Neuronpedia

    INDEX
    Explanations

    expressions related to understanding and communication skills

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

    expressing understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дарю
    -0.38
     Cama
    -0.36
     General
    -0.35
    vid
    -0.35
    неш
    -0.34
    haften
    -0.33
    service
    -0.33
     Tri
    -0.32
    ed
    -0.32
     service
    -0.32
    POSITIVE LOGITS
     Administrativna
    0.81
    parsedMessage
    0.79
    windowFixed
    0.77
     فريبيس
    0.75
     Италијани
    0.74
     незавершена
    0.71
    IntoConstraints
    0.68
    +#+#
    0.68
    tanleria
    0.66
    afficheront
    0.66
    Act Density 0.157%

    No Known Activations