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

    Neuronpedia

    INDEX
    Explanations

    travel enthusiast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     argumentation
    0.41
     somew
    0.39
    `-
    0.38
    シ
    0.38
    `
    0.38
    멜
    0.38
     ソ
    0.37
     stares
    0.37
     campuran
    0.36
     देखी
    0.36
    POSITIVE LOGITS
     Collector
    0.40
    屣
    0.39
    FinishLaunching
    0.39
    ream
    0.38
     Peacock
    0.37
     შეიძ
    0.37
    zty
    0.37
     collector
    0.36
    ugan
    0.36
     paving
    0.36
    Act Density 0.029%

    No Known Activations