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

    Neuronpedia

    INDEX
    Explanations

    morphological, geometry, varied, precise, neuron, RAID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Correo
    0.43
    treas
    0.42
    okovic
    0.40
     Amnesty
    0.39
    回家
    0.39
    wage
    0.39
    kosten
    0.37
    ון
    0.37
    konto
    0.37
     인천
    0.37
    POSITIVE LOGITS
     morphological
    0.48
     morphology
    0.48
     heterogeneity
    0.47
     models
    0.47
     curvature
    0.47
     subtypes
    0.47
     heter
    0.47
     symmetry
    0.47
     symmetrical
    0.47
     large
    0.46
    Act Density 0.093%

    No Known Activations