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

    Neuronpedia

    INDEX
    Explanations

    Story summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elerine
    -0.06
     mpi
    -0.06
    jni
    -0.06
     bush
    -0.06
     KUR
    -0.06
    umu
    -0.06
    double
    -0.06
    iterated
    -0.06
     counselling
    -0.06
     terminate
    -0.06
    POSITIVE LOGITS
    -'+
    0.07
     allows
    0.07
    _pressure
    0.06
     імені
    0.06
     rehab
    0.06
     principally
    0.06
     příst
    0.06
     predomin
    0.06
    rames
    0.06
    ём
    0.06
    Act Density 0.081%

    No Known Activations