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

    Neuronpedia

    INDEX
    Explanations

    video, folder, and weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getDocument
    0.27
     protein
    0.25
     smeared
    0.25
    пада
    0.25
    iveness
    0.25
     coated
    0.25
     panther
    0.23
    ār
    0.23
     fallen
    0.23
    ዐይን
    0.23
    POSITIVE LOGITS
     Momo
    0.30
    㕸
    0.28
     Voice
    0.28
    LeftSide
    0.27
    迪
    0.27
     および
    0.27
    Voice
    0.26
    聲
    0.26
     TL
    0.26
     Sword
    0.26
    Act Density 0.000%

    No Known Activations