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

    Neuronpedia

    INDEX
    Explanations

    common interpretations and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Homemade
    0.44
    observable
    0.44
     observable
    0.43
     verifiable
    0.43
     provenant
    0.42
     punishable
    0.42
     observables
    0.41
    न्ति
    0.41
     можли
    0.40
     Nost
    0.40
    POSITIVE LOGITS
     Elvis
    0.44
    調べて
    0.42
     fris
    0.41
    cnica
    0.41
    擬
    0.40
    ariat
    0.40
     असा
    0.38
    ｹ
    0.38
     Will
    0.38
     hissed
    0.37
    Act Density 0.000%

    No Known Activations