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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and their corresponding variables or expressions

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

    mathematical notation with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.45
     surla
    -0.44
     intptr
    -0.40
     Италијани
    -0.40
     betweenstory
    -0.36
    cuadro
    -0.35
    Solución
    -0.35
    EDEFAULT
    -0.35
     становника
    -0.31
    DeleteBehavior
    -0.31
    POSITIVE LOGITS
     avoient
    0.57
    attutto
    0.54
     étoient
    0.52
     hemd
    0.51
     Perſ
    0.50
     licorne
    0.50
     prenota
    0.49
     mennes
    0.49
    kasse
    0.49
    Mediabestanden
    0.49
    Act Density 0.588%

    No Known Activations