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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Minimal
    -0.08
     Ramadan
    -0.07
     twee
    -0.06
    準
    -0.06
     nu
    -0.06
    PMENT
    -0.06
    HDR
    -0.06
     mænd
    -0.06
    SBATCH
    -0.06
     perse
    -0.06
    POSITIVE LOGITS
     envision
    0.07
    _units
    0.06
    emoji
    0.06
     stating
    0.06
    chlor
    0.06
     Aug
    0.06
    .lift
    0.06
    .hasMore
    0.06
     आप
    0.06
    .intValue
    0.06
    Act Density 0.063%

    No Known Activations