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

    Neuronpedia

    INDEX
    Explanations

    references to options or groups in a comparative context

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

    one of two or three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.48
    évaluateur
    -0.47
    Дереккөздер
    -0.44
     Tenggara
    -0.42
    credits
    -0.41
    ClCompile
    -0.41
    setSuccess
    -0.41
     Photocase
    -0.40
     صح
    -0.40
     Supervision
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.57
    tagHelperRunner
    0.54
     either
    0.49
    ParallelGroup
    0.49
    または
    0.48
    それとも
    0.46
    either
    0.46
     CURIAM
    0.45
    もしくは
    0.44
     opzioni
    0.44
    Act Density 0.022%

    No Known Activations