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

    Neuronpedia

    INDEX
    Explanations

    у, u, in/at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expected
    0.38
     Mat
    0.36
    ABC
    0.36
     दह
    0.36
    Mat
    0.36
    Quantum
    0.35
    xA
    0.35
     drift
    0.35
     OTP
    0.35
     PAF
    0.35
    POSITIVE LOGITS
    olarmente
    0.42
     Phnom
    0.39
    plementation
    0.38
    Lon
    0.38
    leduj
    0.38
    orice
    0.37
     Sacchar
    0.37
    дото
    0.36
    琟
    0.36
    PUT
    0.36
    Act Density 0.001%

    No Known Activations