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

    Neuronpedia

    INDEX
    Explanations

    references to procedures and methods in a variety of contexts

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

    a process or standardized "procedure"

    np_acts-logits-general · gemini-2.0-flash

    procedure or particular aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {{
    -0.77
     Gass
    -0.70
    ा
    -0.69
     magasiner
    -0.69
     AssemblyCulture
    -0.68
    脚注
    -0.67
    ored
    -0.64
     ​​
    -0.63
    ospatial
    -0.63
    ‚¬
    -0.61
    POSITIVE LOGITS
    ']?>
    0.81
    nastics
    0.81
    &=&\
    0.79
     "..\..\
    0.75
    😯
    0.74
    hark
    0.73
    };*/
    0.72
     appContext
    0.72
    ');?>
    0.71
    ]]]
    0.71
    Act Density 0.718%

    No Known Activations