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

    Neuronpedia

    INDEX
    Explanations

    names like Barnaby and Barty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.46
    2
    0.43
    0
    0.41
    ，
    0.37
    8
    0.35
    abouts
    0.33
    4
    0.33
    7
    0.33
    9
    0.33
     besonderen
    0.32
    POSITIVE LOGITS
     be
    0.38
     grandson
    0.36
    ul
    0.36
     Automobile
    0.36
     decommissioning
    0.35
     motorbike
    0.34
    swagen
    0.34
     brake
    0.34
     ಟ
    0.33
    ुक्त
    0.33
    Act Density 0.015%

    No Known Activations