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

    Neuronpedia

    INDEX
    Explanations

    programming functions or methods related to user input and interface interactions

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

    user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.04
     informée
    -0.95
    RenderAtEndOf
    -0.94
    [@BOS@]
    -0.93
    <unused8>
    -0.93
    <unused3>
    -0.93
    <unused42>
    -0.93
    <unused52>
    -0.93
    <unused74>
    -0.93
    <pad>
    -0.93
    POSITIVE LOGITS
    ↵↵
    0.41
     accordingly
    0.35
    2
    0.31
    .
    0.30
    //
    0.30
     podamos
    0.30
     adecuadamente
    0.30
    ↵
    0.29
    if
    0.29
    from
    0.28
    Act Density 0.009%

    No Known Activations