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

    Neuronpedia

    INDEX
    Explanations

    Heimatmuseum uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    صة
    0.48
    imonials
    0.43
     Ото
    0.42
    testimonials
    0.40
     смысл
    0.39
     begren
    0.39
    endon
    0.39
     双
    0.38
     समाप्ति
    0.38
    ጴ
    0.38
    POSITIVE LOGITS
     react
    0.42
     vegetables
    0.41
    ACTIONS
    0.40
     then
    0.37
     टेक्
    0.37
     animals
    0.37
     ke
    0.36
     čak
    0.36
     school
    0.36
     combinations
    0.36
    Act Density 0.001%

    No Known Activations