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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and attributes associated with database management

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

    name, label, or product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    解
    -0.35
     böyle
    -0.32
     pozdě
    -0.30
     násled
    -0.30
     posteriormente
    -0.30
     hicimos
    -0.29
     myö
    -0.28
     fırs
    -0.27
     sahabat
    -0.27
     doświad
    -0.27
    POSITIVE LOGITS
     AssemblyTitle
    0.85
    Personendaten
    0.82
     للاسماء
    0.81
    <pad>
    0.80
    <unused17>
    0.80
    <unused43>
    0.80
    <unused47>
    0.80
    <unused41>
    0.80
    <unused8>
    0.80
    <unused14>
    0.80
    Act Density 0.002%

    No Known Activations