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

    Neuronpedia

    INDEX
    Explanations

    hardware and emulation performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗞
    0.44
     😊
    0.41
     EW
    0.41
     keV
    0.41
     Ć
    0.40
     🥰
    0.40
    餐廳
    0.40
     GCP
    0.39
     選
    0.39
    コーナー
    0.39
    POSITIVE LOGITS
     natively
    0.57
     chipset
    0.55
     overclock
    0.54
    븅
    0.54
    Hardware
    0.53
    Implement
    0.51
     emulation
    0.50
    阉
    0.49
     emulate
    0.49
    处理器
    0.48
    Act Density 0.017%

    No Known Activations