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

    Neuronpedia

    INDEX
    Explanations

    surgery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敦
    -0.07
     Tax
    -0.06
    Photos
    -0.06
     Gamma
    -0.06
    -create
    -0.06
     Access
    -0.06
     Photos
    -0.06
     PROJECT
    -0.06
    -access
    -0.06
    :I
    -0.06
    POSITIVE LOGITS
    crud
    0.08
    .freq
    0.07
    كوم
    0.07
    emmel
    0.07
    arn
    0.07
    ск
    0.07
     šk
    0.06
    Combined
    0.06
     êtes
    0.06
    ateurs
    0.06
    Act Density 0.026%

    No Known Activations