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

    Neuronpedia

    INDEX
    Explanations

    closing braces and related formatting for mathematical expressions

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

    mathematical conditions and inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gött
    -0.38
     verbeter
    -0.37
     néz
    -0.36
     None
    -0.36
     maș
    -0.36
    migrationBuilder
    -0.35
     megold
    -0.34
    None
    -0.33
     żad
    -0.33
    енча
    -0.33
    POSITIVE LOGITS
    itecture
    0.59
    specifier
    0.57
    ftagPool
    0.56
    bolite
    0.56
     floodplain
    0.55
    ikistan
    0.54
    medy
    0.54
    閖
    0.52
    __*/
    0.52
     stalk
    0.51
    Act Density 0.122%

    No Known Activations