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

    Neuronpedia

    INDEX
    Explanations

    text related to programming structures and variables

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    code and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.53
     betweenstory
    -0.53
     Administrativna
    -0.53
    antaranya
    -0.52
     otomatig
    -0.51
    GEBURTSDATUM
    -0.49
    حوالہ
    -0.43
    ۜ
    -0.41
     explosión
    -0.40
    Personendaten
    -0.40
    POSITIVE LOGITS
    endcsname
    0.42
     faſt
    0.40
     cgi
    0.40
     tranſ
    0.40
     BoxFit
    0.40
    Eb
    0.39
    Transkript
    0.39
    ponses
    0.39
    CreateInfo
    0.38
    Bear
    0.38
    Act Density 0.679%

    No Known Activations