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

    Neuronpedia

    INDEX
    Explanations

    ATE/ation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neden
    -0.06
    SizeMode
    -0.06
    ��드
    -0.06
     ubiqu
    -0.06
     Ox
    -0.06
     квар
    -0.06
     сил
    -0.05
     steer
    -0.05
     Ank
    -0.05
    โปรแกรม
    -0.05
    POSITIVE LOGITS
    coll
    0.07
    ATE
    0.07
    AH
    0.07
     ticking
    0.07
    .</
    0.07
     gambling
    0.07
    [source
    0.07
     Jets
    0.07
    房
    0.07
     توجه
    0.07
    Act Density 0.001%

    No Known Activations