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

    Neuronpedia

    INDEX
    Explanations

    nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンの
    -0.07
    есть
    -0.07
     offsetX
    -0.07
    mentioned
    -0.06
    omore
    -0.06
     stále
    -0.06
     деятельности
    -0.06
     після
    -0.06
    mailbox
    -0.06
    ζε
    -0.06
    POSITIVE LOGITS
     screen
    0.06
    _eth
    0.06
    -android
    0.06
    ickey
    0.06
     snakes
    0.06
    classification
    0.06
     بازی
    0.06
     vulnerable
    0.06
     hairstyles
    0.06
    575
    0.06
    Act Density 0.000%

    No Known Activations