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

    Neuronpedia

    INDEX
    Explanations

    references and influences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLASS
    -0.07
     Hol
    -0.06
     Butter
    -0.06
     đá
    -0.06
     ferv
    -0.06
    IZER
    -0.06
    kor
    -0.06
    (ff
    -0.06
     Coloring
    -0.06
     Widow
    -0.06
    POSITIVE LOGITS
     enviado
    0.07
    ('/:
    0.07
     νεφοκάλυψης
    0.07
     센
    0.06
    ворю
    0.06
    @update
    0.06
    _APB
    0.06
    NSNotificationCenter
    0.06
    !");↵
    0.06
    nek
    0.06
    Act Density 0.024%

    No Known Activations