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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     í
    -0.10
     ориент
    -0.08
     Manhattan
    -0.08
     obt
    -0.07
     ലഭ
    -0.07
     oven
    -0.07
     clues
    -0.07
    -0.07
    ITER
    -0.07
     nan
    -0.07
    POSITIVE LOGITS
     intensified
    0.08
    运动
    0.08
     stereotype
    0.08
     overheid
    0.08
    Band
    0.08
    Jet
    0.08
    )((
    0.08
     ಬ್ಯಾಂ
    0.08
    联网
    0.08
    枪
    0.08
    Act Density 0.001%
    No Known Activations