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

    Neuronpedia

    INDEX
    Explanations

    unsafe code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ₂,
    0.44
    sequelize
    0.43
     Ribeiro
    0.42
     अमाउंट
    0.41
    👃
    0.41
     टाइगर
    0.39
    sparsebundle
    0.39
     እየሱስ
    0.39
     자동으로
    0.38
    idać
    0.38
    POSITIVE LOGITS
     menos
    0.47
     mniej
    0.46
     less
    0.44
    च
    0.43
    чки
    0.43
     vượt
    0.43
     meno
    0.42
     check
    0.41
    ט
    0.41
     moins
    0.39
    Act Density 0.020%

    No Known Activations