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

    Neuronpedia

    INDEX
    Explanations

    terms related to examples, references, and guiding principles in various contexts

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

    example, basis, evidence, arguments, reference, gift, input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.38
     ivelany
    -0.37
     parha
    -0.35
     joka
    -0.34
    Sú
    -0.33
     viime
    -0.33
    everything
    -0.32
     iconTwitter
    -0.31
     Roskov
    -0.31
     maraming
    -0.31
    POSITIVE LOGITS
    存于互联网档案馆
    0.58
    الدراسه
    0.56
    ToScroll
    0.55
     GenerationType
    0.52
    tagHelperRunner
    0.52
    enderror
    0.50
    itary
    0.50
    MigrationBuilder
    0.49
     joão
    0.49
    ronpa
    0.48
    Act Density 0.101%

    No Known Activations