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

    Neuronpedia

    INDEX
    Explanations

    Make/Cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -final
    -0.06
    .splitContainer
    -0.06
     Pence
    -0.06
     hesitate
    -0.06
    Clazz
    -0.06
    sez
    -0.06
    Eval
    -0.06
     also
    -0.06
    erse
    -0.06
    posal
    -0.06
    POSITIVE LOGITS
     โรงเร
    0.06
     WR
    0.06
     Sl
    0.06
    	Response
    0.06
    ّد
    0.06
    ******/
    0.06
     Audi
    0.06
     sind
    0.06
     scarc
    0.06
    screen
    0.06
    Act Density 0.074%

    No Known Activations