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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pizza
    -0.08
    орони
    -0.07
    urance
    -0.07
    _armor
    -0.06
    Position
    -0.06
    ُر
    -0.06
    vinc
    -0.06
    gren
    -0.06
    zkum
    -0.06
    lesi
    -0.06
    POSITIVE LOGITS
    ่าม
    0.07
    Instead
    0.06
     selon
    0.06
     apart
    0.06
    (Local
    0.06
     Zack
    0.06
     Episode
    0.06
     Meditation
    0.06
    Init
    0.06
     vow
    0.06
    Act Density 0.119%

    No Known Activations