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

    Neuronpedia

    INDEX
    Explanations

    argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    don
    -0.08
    .SubElement
    -0.07
    ithmetic
    -0.07
    -aware
    -0.06
     Syndrome
    -0.06
    *.
    -0.06
    넨
    -0.06
     psychic
    -0.06
    national
    -0.06
    🐑
    -0.06
    POSITIVE LOGITS
     rootReducer
    0.07
    REAL
    0.07
    是比较
    0.07
     près
    0.07
     imped
    0.07
     hydrated
    0.07
     yüks
    0.07
    .getApp
    0.07
     alkal
    0.07
     IPs
    0.07
    Act Density 0.041%

    No Known Activations