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

    Neuronpedia

    INDEX
    Explanations

    responsible for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    代码
    0.50
    ে
    0.43
    たく
    0.42
     idiom
    0.42
    年
    0.42
     kó
    0.41
    刻
    0.40
    生命
    0.40
    强制
    0.40
     doubt
    0.40
    POSITIVE LOGITS
    uzzo
    0.50
    acom
    0.50
    ICAGO
    0.50
    HPLC
    0.49
    Primo
    0.48
    Neben
    0.48
    unächst
    0.48
    Hilo
    0.48
    IA
    0.48
    CAUSE
    0.48
    Act Density 0.020%

    No Known Activations