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

    Neuronpedia

    INDEX
    Explanations

    references to input and output parameters in technical specifications or programming contexts

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

    output or destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лтамалар
    -0.73
    RefNanny
    -0.70
     AssemblyCulture
    -0.69
     transfieras
    -0.68
    extAlignment
    -0.68
     мәкал
    -0.64
     يتيمه
    -0.63
    хівовано
    -0.60
     wireType
    -0.60
    findpost
    -0.60
    POSITIVE LOGITS
     menyesuaikan
    0.31
     olacak
    0.31
    łaści
    0.27
     edili
    0.27
     rescate
    0.26
     ediyor
    0.26
     fatale
    0.25
     türlü
    0.25
     eint
    0.24
    fikation
    0.24
    Act Density 0.074%

    No Known Activations