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

    Neuronpedia

    INDEX
    Explanations

    references to statistical values or significance markers in research data

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

    numbers or position indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incertidumbre
    -0.29
     despedida
    -0.29
     şun
    -0.29
     únicos
    -0.28
     žem
    -0.28
     felé
    -0.28
     únicas
    -0.28
     Grüsse
    -0.27
     şöyle
    -0.27
     ternura
    -0.26
    POSITIVE LOGITS
     ſei
    0.82
    ஦
    0.79
    ſelben
    0.79
     ſeines
    0.79
     ſeiner
    0.79
    <unused14>
    0.79
    <unused41>
    0.79
    <unused79>
    0.79
    <unused16>
    0.79
    <unused8>
    0.79
    Act Density 0.031%

    No Known Activations