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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dakota
    -0.08
     riff
    -0.08
    口碑
    -0.07
    假日
    -0.07
    -training
    -0.07
    ӏ
    -0.07
     disgr
    -0.07
    🍠
    -0.07
     pamię
    -0.07
     Kitchen
    -0.07
    POSITIVE LOGITS
     blinked
    0.07
    师
    0.06
     structures
    0.06
    DTO
    0.06
    (stat
    0.06
    ပ
    0.06
    훵
    0.06
    -de
    0.06
    	dispatch
    0.06
    㙘
    0.06
    Act Density 0.002%

    No Known Activations