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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יטי
    -0.08
    Signin
    -0.07
     exclude
    -0.07
     Tages
    -0.07
    apal
    -0.07
     টি
    -0.07
     Lov
    -0.07
     gering
    -0.07
     PAD
    -0.07
     lin
    -0.07
    POSITIVE LOGITS
    wine
    0.08
     Oriental
    0.08
    ❤️
    0.08
     Oriente
    0.08
    Interesting
    0.07
     आगे
    0.07
    ————
    0.07
    (":
    0.07
    ——
    0.07
     nā
    0.07
    Act Density 0.000%

    No Known Activations