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

    Neuronpedia

    INDEX
    Explanations

    references to logical reasoning and criteria

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

    logic / rules / reason / governing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __*/
    -0.49
    ulemon
    -0.47
    Ecotoxicity
    -0.45
    PYX
    -0.43
     Walkover
    -0.41
    endpush
    -0.41
     étoient
    -0.40
    swal
    -0.40
    
    -0.39
    Rüyada
    -0.39
    POSITIVE LOGITS
     logic
    0.56
    RULES
    0.54
     rules
    0.54
     regras
    0.53
     rule
    0.52
     algorithm
    0.52
    +#+#
    0.52
    ftagPool
    0.50
     criterios
    0.50
     lógica
    0.49
    Act Density 0.368%

    No Known Activations