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

    Neuronpedia

    INDEX
    Explanations

    keyloggers record everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    family
    0.44
    don
    0.44
     family
    0.44
     company
    0.41
    جة
    0.41
     myself
    0.41
    自己
    0.40
    cdn
    0.40
     sini
    0.39
    I
    0.39
    POSITIVE LOGITS
    搛
    0.50
     pumped
    0.50
     transmitted
    0.48
     всіх
    0.46
     termasuk
    0.46
     එ
    0.45
     froze
    0.45
     iterated
    0.45
     kept
    0.45
     exercised
    0.45
    Act Density 0.001%

    No Known Activations