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

    Neuronpedia

    INDEX
    Explanations

    code examples and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Had
    0.43
     HAD
    0.41
     Had
    0.40
    ್‌
    0.37
    had
    0.37
    Appropri
    0.36
    out
    0.36
     vissa
    0.35
     condenser
    0.34
    vis
    0.34
    POSITIVE LOGITS
    anson
    0.42
    imore
    0.42
     Gy
    0.40
    NSE
    0.40
    nSamples
    0.39
     궁금
    0.39
    Gyro
    0.39
    몰
    0.39
     Gunnar
    0.38
     At
    0.38
    Act Density 0.001%

    No Known Activations