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

    Neuronpedia

    INDEX
    Explanations

    each client

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    なかったので
    0.39
     существо
    0.39
     MCT
    0.37
    CONDUCT
    0.37
    Exist
    0.35
    dQ
    0.35
    zq
    0.35
    唃
    0.35
    Exists
    0.35
    ilk
    0.34
    POSITIVE LOGITS
    obby
    0.41
    omet
    0.38
    પ્
    0.38
    eggi
    0.38
    ála
    0.37
     Tenn
    0.37
     ér
    0.37
     mainline
    0.37
     बँके
    0.37
    omey
    0.37
    Act Density 0.000%

    No Known Activations