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

    Neuronpedia

    INDEX
    Explanations

    no question is too simple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     координаты
    0.50
     cornice
    0.49
     usb
    0.49
     powertrain
    0.48
     ragazzi
    0.48
     lindos
    0.48
     justiça
    0.47
     moose
    0.47
     thousand
    0.46
     raza
    0.46
    POSITIVE LOGITS
    Dry
    0.48
    积极
    0.46
    jár
    0.46
    गी
    0.41
    Gl
    0.40
    现代
    0.40
    gel
    0.40
    Examples
    0.39
    bücher
    0.39
    Vu
    0.39
    Act Density 0.001%

    No Known Activations