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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act · gemini-2.0-flash

    Python code related to data handling and model training in machine learning.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     태
    -0.07
    oretical
    -0.07
     خوش
    -0.07
    -free
    -0.07
    hoot
    -0.06
     Tik
    -0.06
    -fields
    -0.06
     imperfect
    -0.06
    さい
    -0.06
    (reference
    -0.06
    POSITIVE LOGITS
    0.07
    _CFG
    0.06
    ，被
    0.06
    ])(
    0.06
    _string
    0.06
    (account
    0.06
     rental
    0.06
    [String
    0.06
     IndexPath
    0.06
     allegedly
    0.06
    Act Density 0.005%

    No Known Activations