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

    Neuronpedia

    INDEX
    Explanations

    logical constructs and relationships in mathematical or statistical contexts

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

    special case $A$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.53
    KURZBESCHREIBUNG
    -0.44
    HtmlAttribute
    -0.42
    UnusedPrivate
    -0.41
     Exactos
    -0.40
    Personendaten
    -0.38
     nakalista
    -0.38
    MigrationBuilder
    -0.38
    Derp
    -0.37
    geslacht
    -0.37
    POSITIVE LOGITS
     المعيارى
    0.51
     gynhyrchwyd
    0.44
     للمعارف
    0.44
     للاسماء
    0.43
    0.42
    uvwxyz
    0.42
     okuyayım
    0.41
    };*/
    0.40
    endpush
    0.40
    \{\\
    0.40
    Act Density 0.368%

    No Known Activations