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

    Neuronpedia

    INDEX
    Explanations

    detailed explanations and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.29
    (
    0.28
    -
    0.27
    Initializing
    0.25
     gleichen
    0.25
    ₱
    0.24
    <0xA0>
    0.24
    \'
    0.24
    \&
    0.24
     erforderlich
    0.23
    POSITIVE LOGITS
     the
    0.32
     people
    0.30
     in
    0.30
     do
    0.29
     been
    0.29
     your
    0.27
     hit
    0.27
     legal
    0.27
     on
    0.26
     these
    0.26
    Act Density 0.853%

    No Known Activations