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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mountains
    -0.07
     mountains
    -0.07
     rif
    -0.07
     Ward
    -0.07
    алізації
    -0.07
     дума
    -0.07
    xCA
    -0.06
    уры
    -0.06
     галуз
    -0.06
    Allen
    -0.06
    POSITIVE LOGITS
    )이
    0.07
     decoder
    0.06
     빛
    0.06
    Talking
    0.06
    sect
    0.06
    ια
    0.06
    ünk
    0.06
    ?#
    0.06
     bitmap
    0.06
     جه
    0.06
    Act Density 0.002%

    No Known Activations