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

    Neuronpedia

    INDEX
    Explanations

    cannot action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    რო
    0.48
     Nếu
    0.46
    미
    0.45
    plotting
    0.45
     Correction
    0.44
     Scattering
    0.44
    altering
    0.44
    spannung
    0.44
     Allocation
    0.44
    트
    0.43
    POSITIVE LOGITS
     withstand
    0.68
     afford
    0.64
     accommodate
    0.62
     identify
    0.55
     handle
    0.52
     navigate
    0.52
     tolerate
    0.52
     convince
    0.51
     discern
    0.50
     quantify
    0.50
    Act Density 0.195%

    No Known Activations