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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Promise
    -0.06
    robots
    -0.06
    مار
    -0.06
    к
    -0.06
     UNITY
    -0.06
     blinded
    -0.06
    issent
    -0.06
     np
    -0.06
    culus
    -0.06
     Distance
    -0.06
    POSITIVE LOGITS
     »↵
    0.07
    ‌پ
    0.07
    )(__
    0.07
    (df
    0.06
     뿐
    0.06
    (Constructor
    0.06
    /test
    0.06
    (da
    0.06
    expected
    0.06
    /scripts
    0.06
    Act Density 0.011%

    No Known Activations