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

    Neuronpedia

    INDEX
    Explanations

    programs for, Cutting exposes, fluid to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adams
    0.41
     establishment
    0.40
     households
    0.39
     Abrams
    0.39
     practitioner
    0.39
     settings
    0.39
     order
    0.38
     onboard
    0.38
     Peters
    0.38
     Hammond
    0.38
    POSITIVE LOGITS
     financeira
    0.49
    etian
    0.46
     financiera
    0.44
    arquivo
    0.41
     فایل
    0.41
     plabic
    0.41
     quadrada
    0.40
     tärke
    0.40
    tochy
    0.40
    Crossing
    0.40
    Act Density 0.000%

    No Known Activations