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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    357
    -0.07
     tvrd
    -0.07
     şaş
    -0.07
    費
    -0.07
     enslaved
    -0.07
    (utils
    -0.06
    (Constant
    -0.06
     açı
    -0.06
    .lon
    -0.06
     κο
    -0.06
    POSITIVE LOGITS
    ασίας
    0.07
    hc
    0.06
    iltere
    0.06
    ним
    0.06
    ocity
    0.06
    Transport
    0.06
    jn
    0.06
     peek
    0.06
    phia
    0.06
    笔
    0.06
    Act Density 0.060%

    No Known Activations