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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suministros
    -0.31
     meilleurs
    -0.30
     Kepala
    -0.30
    isième
    -0.29
     adquis
    -0.28
     nadie
    -0.28
     mohou
    -0.27
    gjenge
    -0.27
     prosjek
    -0.27
    kuuta
    -0.26
    POSITIVE LOGITS
    SequentialGroup
    0.86
     للاسماء
    0.84
    co
    0.79
    awtextra
    0.79
    <unused42>
    0.78
    [@BOS@]
    0.78
    <unused52>
    0.78
    omitempty
    0.78
    ſelben
    0.78
    <unused3>
    0.78
    Act Density 0.001%

    No Known Activations