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

    Neuronpedia

    INDEX
    Explanations

    programming method signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.40
    1
    0.40
     tgt
    0.37
     gagner
    0.36
     fulfills
    0.35
     proprement
    0.35
     nField
    0.35
    (\
    0.34
    ?
    0.34
    2
    0.34
    POSITIVE LOGITS
    <unused301>
    0.47
    <unused995>
    0.46
    <unused283>
    0.44
    <unused1864>
    0.44
    <unused501>
    0.44
     ఇతర
    0.43
    <unused1882>
    0.43
    <unused733>
    0.43
    <unused981>
    0.43
    <unused421>
    0.42
    Act Density 0.000%

    No Known Activations