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

    Neuronpedia

    INDEX
    Explanations

    outside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PostgreSQL
    -0.08
     Př
    -0.07
     PŘ
    -0.07
    ign
    -0.06
    õi
    -0.06
     Citation
    -0.06
     Related
    -0.06
    293
    -0.06
     ESC
    -0.06
     atd
    -0.06
    POSITIVE LOGITS
     virtue
    0.07
     UserProfile
    0.07
     trench
    0.06
    APT
    0.06
    ewise
    0.06
    илось
    0.06
     Edinburgh
    0.06
    된다
    0.06
    /cache
    0.06
    决定
    0.06
    Act Density 0.021%

    No Known Activations