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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alcohol
    -0.08
    む
    -0.07
    Wnd
    -0.07
    ystate
    -0.07
     급
    -0.07
    측
    -0.07
    -X
    -0.07
    slashes
    -0.07
    اظ
    -0.07
    Wall
    -0.07
    POSITIVE LOGITS
    ###↵
    0.07
     divide
    0.07
     پش
    0.06
     ऐस
    0.06
     بین
    0.06
     mindful
    0.06
     projecting
    0.06
    átel
    0.06
     parchment
    0.06
    (parsed
    0.06
    Act Density 0.002%

    No Known Activations