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

    Neuronpedia

    INDEX
    Explanations

    chin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çö
    -0.08
     Broadcasting
    -0.08
     Reconstruction
    -0.08
     reconstruction
    -0.08
     görül
    -0.08
     relativa
    -0.07
     размест
    -0.07
    рий
    -0.07
     کرونا
    -0.07
     Tv
    -0.07
    POSITIVE LOGITS
     tuck
    0.08
     drain
    0.08
     pulley
    0.08
     draining
    0.08
    يرة
    0.07
    负
    0.07
    ucking
    0.07
     drains
    0.07
     forbed
    0.07
     객
    0.07
    Act Density 0.001%

    No Known Activations