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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nd
    -0.07
     му
    -0.07
     Trying
    -0.07
    怪
    -0.06
    ют
    -0.06
     difer
    -0.06
     бух
    -0.06
    irket
    -0.06
    onomous
    -0.06
    に対
    -0.06
    POSITIVE LOGITS
    pr
    0.07
    _action
    0.07
    cases
    0.07
    _areas
    0.06
    JOIN
    0.06
    น
    0.06
    iropr
    0.06
    erals
    0.06
     graceful
    0.06
     illustration
    0.06
    Act Density 0.020%

    No Known Activations