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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inges
    -0.06
     locked
    -0.06
     dünyanın
    -0.06
     hayal
    -0.06
    	as
    -0.06
     мере
    -0.06
     결혼
    -0.06
    ái
    -0.06
    _TYPES
    -0.06
     produtos
    -0.06
    POSITIVE LOGITS
     fails
    0.07
     synonymous
    0.07
    0.07
     NUM
    0.07
    ={'
    0.07
     ASSERT
    0.07
     clipboard
    0.07
    fair
    0.07
    android
    0.07
    (Camera
    0.07
    Act Density 0.009%

    No Known Activations