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

    Neuronpedia

    INDEX
    Explanations

    decide whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {\$
    0.46
     UpdateWindow
    0.44
     ministerial
    0.43
    绚
    0.43
    %%%%%%%%%%%%
    0.42
     शैली
    0.41
     해석
    0.41
     userRepository
    0.41
    但我
    0.41
    ']
    0.40
    POSITIVE LOGITS
    ✘
    0.46
    Bare
    0.43
    al
    0.41
     zabezpie
    0.40
    म्प्ट
    0.40
    in
    0.40
    INE
    0.40
    Ly
    0.40
    ണ്ടാ
    0.40
    க
    0.40
    Act Density 0.001%

    No Known Activations