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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     historic
    -0.07
    amax
    -0.06
    attended
    -0.06
    患
    -0.06
    ců
    -0.06
    ils
    -0.06
    amos
    -0.06
    200
    -0.06
    śmy
    -0.06
     Sidney
    -0.06
    POSITIVE LOGITS
     disregard
    0.06
    Cre
    0.06
    _intent
    0.06
     목소
    0.06
     Nadu
    0.06
     Me
    0.06
     darüber
    0.06
     Cre
    0.06
     Heating
    0.06
     χρη
    0.06
    Act Density 0.042%

    No Known Activations