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

    Neuronpedia

    INDEX
    Explanations

    specific phonetic or orthographic patterns in multiple languages

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

    Non-English text or characters

    np_acts-logits-general · gemini-2.0-flash

    esthetic, Entführung, Establecer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.46
    בודה
    -0.44
    __':
    -0.42
    ]");
    -0.42
    principalColumn
    -0.42
     régions
    -0.41
     chrétiens
    -0.41
    تقاوى
    -0.41
    __':
    -0.41
    راتيج
    -0.38
    POSITIVE LOGITS
    elfth
    0.73
     {#
    0.63
    ViewFeatures
    0.61
    detto
    0.60
    erobic
    0.60
     Invited
    0.59
     effusion
    0.59
     Ababa
    0.59
    yntaxException
    0.58
    Ashlee
    0.58
    Act Density 0.080%

    No Known Activations