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
    _CONNECTED
    -0.07
     Dahl
    -0.07
     температу
    -0.06
     tep
    -0.06
     во
    -0.06
    ickle
    -0.06
     березня
    -0.06
     pressures
    -0.06
     ℝ
    -0.06
    /al
    -0.05
    POSITIVE LOGITS
    	I
    0.07
    _sheet
    0.07
     Ded
    0.07
     Shelby
    0.07
     Builds
    0.07
     Shopping
    0.07
     discourse
    0.07
     아직
    0.07
     Topics
    0.06
     Theory
    0.06
    Act Density 0.009%

    No Known Activations