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

    Neuronpedia

    INDEX
    Explanations

    Naruto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澍
    -0.07
     recycle
    -0.07
    火花
    -0.07
     vastly
    -0.07
    랰
    -0.07
    羹
    -0.07
     asphalt
    -0.07
    赓
    -0.07
    Ҁ
    -0.07
     Draft
    -0.07
    POSITIVE LOGITS
    +(\
    0.07
     **
    0.07
    問い
    0.07
    modes
    0.06
    (place
    0.06
    (slot
    0.06
    (point
    0.06
    datos
    0.06
     dialog
    0.06
    Tri
    0.06
    Act Density 0.010%

    No Known Activations