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

    Neuronpedia

    INDEX
    Explanations

    purpose or function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Protocol
    0.52
    Diagram
    0.51
     piernas
    0.50
    DetailUI
    0.50
     yeux
    0.49
    ⏫
    0.47
    рены
    0.47
    রচনা
    0.46
     Adası
    0.46
    넴
    0.46
    POSITIVE LOGITS
    to
    0.59
    as
    0.44
     VARI
    0.43
     J
    0.43
     Philippine
    0.43
    。
    0.41
     T
    0.41
    if
    0.41
     Prussians
    0.40
    ш
    0.40
    Act Density 0.001%

    No Known Activations