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

    Neuronpedia

    INDEX
    Explanations

    vary, impact, required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isVideoRecording
    0.43
     stature
    0.43
     항상
    0.42
    чів
    0.42
    ቱም
    0.40
    getBlueTeam
    0.40
     cancelButton
    0.39
     お知らせ
    0.39
     그린
    0.39
     Floret
    0.38
    POSITIVE LOGITS
    :
    0.66
    *:
    0.50
     especial
    0.49
     selen
    0.46
     Ile
    0.45
     deuda
    0.45
    μος
    0.44
    :"
    0.44
     debat
    0.42
     dienst
    0.42
    Act Density 0.005%

    No Known Activations