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

    Neuronpedia

    INDEX
    Explanations

    critical terms related to statistical analysis or evaluation parameters

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

    three become

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gyhoeddwyd
    -0.86
    Diweddarwch
    -0.70
     चीज़ों
    -0.69
     ModelExpression
    -0.68
    كويكب
    -0.64
     AspNetCore
    -0.61
    WriteBarrier
    -0.60
     protoimpl
    -0.60
     يتيمه
    -0.59
     InputDecoration
    -0.58
    POSITIVE LOGITS
    E
    0.30
    <eos>
    0.30
    Re
    0.30
    ((
    0.30
    Cross
    0.30
    <h1>
    0.30
    eci
    0.30
     poly
    0.29
    No
    0.28
    biór
    0.28
    Act Density 0.145%

    No Known Activations