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

    Neuronpedia

    INDEX
    Explanations

    setting AI model parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פשר
    0.38
    ｜
    0.37
     Rica
    0.36
     subgraph
    0.36
    して
    0.36
     Drug
    0.35
     rowing
    0.35
     précédents
    0.35
     Poi
    0.35
    looms
    0.35
    POSITIVE LOGITS
    response
    0.40
    嗳
    0.37
    titleTextStyle
    0.37
    訊息
    0.37
     response
    0.37
    arris
    0.36
     엔진
    0.36
    ESSAGE
    0.35
     fw
    0.35
    RESPONSE
    0.35
    Act Density 0.006%

    No Known Activations