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

    Neuronpedia

    INDEX
    Explanations

    foreign language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.53
    ponen
    0.52
    z
    0.52
    ue
    0.49
    TP
    0.49
    ge
    0.49
    ור
    0.48
    \}\
    0.47
    ok
    0.46
    xas
    0.46
    POSITIVE LOGITS
     регули
    0.50
    વે
    0.47
     âm
    0.47
     Boxing
    0.47
     ආරක්ෂ
    0.46
     aggrieved
    0.46
     airson
    0.46
     është
    0.46
     Mujer
    0.45
     unequivocally
    0.45
    Act Density 0.001%

    No Known Activations