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

    Neuronpedia

    INDEX
    Explanations

    linked to, derived from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     taxi
    0.73
     główn
    0.70
    छा
    0.70
     थी
    0.67
    Taxi
    0.67
    м
    0.67
     Ory
    0.66
    élève
    0.65
    挚
    0.65
     दुकानदार
    0.64
    POSITIVE LOGITS
     discontinuities
    0.74
     tertentu
    0.73
     perturbations
    0.72
     paradigms
    0.71
     Reference
    0.70
     isomorphisms
    0.70
     Variablen
    0.66
     clusters
    0.66
     singularities
    0.64
     hierarchies
    0.63
    Act Density 0.016%

    No Known Activations