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

    Neuronpedia

    INDEX
    Explanations

    General text and reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burning
    -0.07
     Roe
    -0.07
    gger
    -0.07
     더
    -0.06
     đủ
    -0.06
     heavenly
    -0.06
     spawning
    -0.06
     Abbas
    -0.06
    Ma
    -0.06
    енными
    -0.06
    POSITIVE LOGITS
    -chan
    0.08
     jacket
    0.07
    ثیر
    0.06
    tridges
    0.06
    _proba
    0.06
     Helpful
    0.06
    ays
    0.06
     jackets
    0.06
     Lastly
    0.06
    AYS
    0.06
    Act Density 0.000%

    No Known Activations