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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific measurement and analysis

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

    Scientific or technical terms

    np_acts-logits-general · gemini-2.0-flash

    interactions and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.55
     للاسماء
    -0.55
     @}
    -0.52
    messi
    -0.51
     vokal
    -0.50
     ioutil
    -0.46
     vicina
    -0.46
     lauter
    -0.45
    ➽
    -0.45
     itself
    -0.44
    POSITIVE LOGITS
     combo
    1.07
     ratio
    1.00
     relationship
    0.98
     combination
    0.97
     hybrid
    0.86
     relations
    0.80
     interface
    0.80
    relationship
    0.79
     combos
    0.79
     interaction
    0.79
    Act Density 0.618%

    No Known Activations