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

    Neuronpedia

    INDEX
    Explanations

    or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isomorphisms
    0.60
     hallucinations
    0.57
     the
    0.53
     kayaks
    0.52
     reptiles
    0.52
     vampires
    0.51
     NPCs
    0.51
     superheroes
    0.50
     tortillas
    0.49
     touchdowns
    0.49
    POSITIVE LOGITS
     কিংবা
    0.62
     or
    0.61
     или
    0.59
    或
    0.53
     किंवा
    0.52
    または
    0.52
     atau
    0.51
    又は
    0.50
     یا
    0.49
     või
    0.49
    Act Density 0.258%

    No Known Activations