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

    Neuronpedia

    INDEX
    Explanations

    fiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alarında
    -0.07
    加载
    -0.07
     lakes
    -0.07
    Extract
    -0.06
     Unlock
    -0.06
     inspire
    -0.06
     courtyard
    -0.06
    ทะ
    -0.06
     LETTER
    -0.06
    ga
    -0.06
    POSITIVE LOGITS
     fiction
    0.16
     Fiction
    0.12
    -fiction
    0.09
    fiction
    0.09
    (enc
    0.07
     Liam
    0.07
    ，此
    0.07
     fanc
    0.07
     erotica
    0.07
     bec
    0.07
    Act Density 0.005%

    No Known Activations