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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DisplayName
    -0.07
     than
    -0.07
    ain
    -0.07
    adj
    -0.07
     plays
    -0.06
    ounce
    -0.06
    áli
    -0.06
     Selling
    -0.06
    _destination
    -0.06
    umar
    -0.06
    POSITIVE LOGITS
    vector
    0.08
     vector
    0.07
     prům
    0.07
    532
    0.07
    0.07
     weaving
    0.06
     negate
    0.06
     сел
    0.06
     zvol
    0.06
    fov
    0.06
    Act Density 0.002%

    No Known Activations