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

    Neuronpedia

    INDEX
    Explanations

    dark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lastIndex
    -0.07
    이어
    -0.06
     çıkan
    -0.06
    iliz
    -0.06
     territorial
    -0.06
    .UN
    -0.06
    하고
    -0.06
    .dylib
    -0.06
    orraine
    -0.06
    وی
    -0.06
    POSITIVE LOGITS
    	dest
    0.07
     suffering
    0.07
    	source
    0.07
     norms
    0.07
     institutes
    0.06
     mane
    0.06
    heit
    0.06
     art
    0.06
    async
    0.06
     dudes
    0.06
    Act Density 0.005%

    No Known Activations