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

    Neuronpedia

    INDEX
    Explanations

    cooking, protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bueno
    0.51
    Planning
    0.51
    emplates
    0.50
    ர
    0.50
    Centro
    0.48
    وٹی
    0.48
    Suzanne
    0.47
    ኖ
    0.46
    Caprio
    0.45
    珽
    0.45
    POSITIVE LOGITS
    ný
    0.49
    a
    0.48
     inferred
    0.47
     academic
    0.46
    ));
    0.46
     was
    0.45
    \
    0.45
    avac
    0.44
    gas
    0.44
     volatiles
    0.44
    Act Density 0.003%

    No Known Activations