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

    Neuronpedia

    INDEX
    Explanations

    upside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mockito
    -0.06
     Tk
    -0.06
     Bits
    -0.06
     tk
    -0.06
    ():
↵
    -0.06
    (guess
    -0.06
    oxel
    -0.06
    (rb
    -0.06
    (torch
    -0.06
    œ
    -0.06
    POSITIVE LOGITS
     στους
    0.07
     BOOL
    0.06
     dab
    0.06
    IZED
    0.06
    /car
    0.06
     bang
    0.06
    동
    0.06
    abar
    0.06
     действия
    0.06
     dood
    0.06
    Act Density 0.009%

    No Known Activations