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

    Neuronpedia

    INDEX
    Explanations

    purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енности
    -0.07
    arrow
    -0.07
     زن
    -0.07
     jpeg
    -0.07
     Mehr
    -0.06
    otts
    -0.06
    clf
    -0.06
     newVal
    -0.06
     anzeigen
    -0.06
    (conv
    -0.06
    POSITIVE LOGITS
     Native
    0.07
     complains
    0.06
    一直
    0.06
    ppelin
    0.06
     ข
    0.06
    Luck
    0.06
    IK
    0.06
     Illegal
    0.06
     vase
    0.06
     Antoine
    0.06
    Act Density 0.001%

    No Known Activations