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

    Neuronpedia

    INDEX
    Explanations

    references to system integration and operational methods

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

    switching and changing states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſol
    -0.71
     ſon
    -0.64
     faſt
    -0.64
     ſta
    -0.63
     ſch
    -0.61
     ſte
    -0.61
     deſt
    -0.59
     houſe
    -0.59
     itſelf
    -0.59
     poffible
    -0.59
    POSITIVE LOGITS
     instead
    0.48
    instead
    0.42
    に変更
    0.42
     Instead
    0.40
    Instead
    0.40
     transitioned
    0.38
    альное
    0.38
    脚注の使い方
    0.38
     transitioning
    0.37
    轉
    0.37
    Act Density 0.127%

    No Known Activations