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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "is" in various contexts

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

    programmers and multilingual labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſei
    -0.60
    <unused79>
    -0.59
    [@BOS@]
    -0.59
    <unused8>
    -0.59
    <unused23>
    -0.59
    <unused17>
    -0.59
    <unused51>
    -0.59
    <unused52>
    -0.59
    <unused3>
    -0.59
    <unused16>
    -0.59
    POSITIVE LOGITS
    altezza
    0.35
    posób
    0.33
     originalen
    0.32
     nôtre
    0.29
    TargetException
    0.29
    LookAnd
    0.29
     mía
    0.28
     zij
    0.28
    ENCODING
    0.28
    inados
    0.28
    Act Density 0.013%

    No Known Activations