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

    Neuronpedia

    INDEX
    Explanations

    terms related to directional technology or concepts

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

    directional detection selection modulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (/^
    -0.51
    脚注の使い方
    -0.43
     LoginPage
    -0.40
    toPromise
    -0.40
     상세
    -0.39
    disposing
    -0.38
    APPENDIX
    -0.38
    Sucesor
    -0.38
    は何
    -0.38
    Atsauces
    -0.37
    POSITIVE LOGITS
    directional
    2.17
     directional
    2.05
    irectional
    2.00
     Directional
    1.98
    Directional
    1.97
     bidirectional
    1.02
    DIRECTION
    0.93
     DIRECTION
    0.92
    定向
    0.85
    directions
    0.79
    Act Density 0.008%

    No Known Activations