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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itives
    -0.08
     explosion
    -0.07
    Understanding
    -0.07
     []
    -0.07
     ballot
    -0.07
     остров
    -0.07
     місце
    -0.06
     superintendent
    -0.06
     swore
    -0.06
    μοί
    -0.06
    POSITIVE LOGITS
    enting
    0.08
     aldı
    0.07
    vál
    0.06
    -mode
    0.06
    價
    0.06
    NibName
    0.06
     좀
    0.06
     بی
    0.06
        
    0.06
     GHz
    0.06
    Act Density 0.006%

    No Known Activations