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

    Neuronpedia

    INDEX
    Explanations

    terms related to fundamental principles and scripting elements

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

    fundamental, in principle, basically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.48
    ArgsConstructor
    -0.47
     ontstaan
    -0.45
     ocurrido
    -0.45
    jidad
    -0.43
     ब्रेकडाउन
    -0.43
    ècie
    -0.42
    dă
    -0.41
     Wad
    -0.41
    alah
    -0.40
    POSITIVE LOGITS
    基本
    1.46
     基本
    1.13
    的基本
    0.82
    の基本
    0.67
    基本的
    0.63
    ほぼ
    0.56
    Basic
    0.55
    殆
    0.53
     tetap
    0.53
    principalTable
    0.52
    Act Density 0.003%

    No Known Activations