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

    Neuronpedia

    INDEX
    Explanations

    by default, by far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    但也
    0.82
    但
    0.81
     відповідно
    0.81
    durch
    0.75
     சேர்ந்து
    0.74
    я
    0.72
    یه
    0.70
    但是
    0.69
     чрез
    0.69
    helle
    0.69
    POSITIVE LOGITS
     definition
    1.79
     far
    1.61
     default
    1.58
     contrast
    1.54
     virtue
    1.52
    definition
    1.46
     way
    1.37
     comparison
    1.36
    zantine
    1.33
     FAR
    1.32
    Act Density 0.039%

    No Known Activations