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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    domain
    -0.07
    ко
    -0.06
     Elena
    -0.06
    _ne
    -0.06
    goo
    -0.06
    levant
    -0.06
     autocomplete
    -0.06
    Compression
    -0.06
    .watch
    -0.06
     relevant
    -0.06
    POSITIVE LOGITS
     вспом
    0.07
     itir
    0.06
     çalışmalar
    0.06
    _FM
    0.06
     özellikle
    0.06
     Sinh
    0.06
    	Runtime
    0.06
     vedle
    0.06
     outweigh
    0.06
     getById
    0.06
    Act Density 0.027%

    No Known Activations