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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and parameters involving structured data interactions

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

    mathematical expressions with exponentiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.37
     ready
    -0.31
    <eos>
    -0.29
     מע
    -0.29
     true
    -0.28
     and
    -0.28
     laissé
    -0.28
     beraber
    -0.27
     laiss
    -0.27
    руктура
    -0.26
    POSITIVE LOGITS
    rungsseite
    0.77
     queſto
    0.71
     ब्रेकडाउन
    0.69
    iſche
    0.69
    <unused8>
    0.69
    <unused41>
    0.69
    <unused68>
    0.69
    <unused28>
    0.69
    [@BOS@]
    0.69
    <unused14>
    0.69
    Act Density 0.078%

    No Known Activations