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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating usage or application of methods and principles in problem-solving contexts

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

    explaining with theorem or proof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Philist
    -0.48
     Samaria
    -0.47
    SBATCH
    -0.46
     roth
    -0.45
     Amphi
    -0.45
     DMSO
    -0.45
    Slf
    -0.43
    RRect
    -0.43
    argout
    -0.42
     Deserialize
    -0.42
    POSITIVE LOGITS
    DeleteBehavior
    0.46
     zwey
    0.41
     caminhada
    0.41
     geren
    0.41
    kháu
    0.41
     válida
    0.40
     aplicable
    0.40
     nonUne
    0.39
    ölkerung
    0.39
     Wikiseite
    0.38
    Act Density 0.028%

    No Known Activations