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

    Neuronpedia

    INDEX
    Explanations

    business models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uatu
    0.77
    liste
    0.75
    lardan
    0.75
    olome
    0.73
    mtrl
    0.72
    genome
    0.72
    ल्ज
    0.72
    xiii
    0.71
    give
    0.71
    ri
    0.71
    POSITIVE LOGITS
     afirmar
    0.87
     hashed
    0.78
     insists
    0.77
     hashes
    0.74
     הוא
    0.72
     hopped
    0.72
    hoppers
    0.72
     affirms
    0.71
    から
    0.70
     otherwise
    0.69
    Act Density 0.002%

    No Known Activations