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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ರಿಂದ
    -0.07
    Cyber
    -0.07
    arlos
    -0.07
    kiä
    -0.07
    SEE
    -0.07
    _GROUP
    -0.07
    ဳ
    -0.07
    කි
    -0.07
    Ultimately
    -0.07
     структур
    -0.07
    POSITIVE LOGITS
     captivated
    0.09
     filled
    0.08
     Aufmerksamkeit
    0.08
     Tunes
    0.08
     blasting
    0.08
     headlines
    0.08
     распрост
    0.08
     dazz
    0.08
     boldly
    0.08
     amazed
    0.08
    Act Density 0.098%

    No Known Activations