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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to make" and "to do" in multiple languages

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

    make or do or realize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PyExc
    -0.57
    IntoConstraints
    -0.52
    migrationBuilder
    -0.52
     mijne
    -0.51
     normalidad
    -0.50
    chließend
    -0.49
     niitä
    -0.49
    oplayer
    -0.49
     camioneta
    -0.46
     Geſch
    -0.46
    POSITIVE LOGITS
     done
    0.73
     kész
    0.69
     wykon
    0.69
     made
    0.66
     executed
    0.65
     réalisé
    0.65
    done
    0.63
     réalise
    0.63
     сделан
    0.61
     wykona
    0.61
    Act Density 0.092%

    No Known Activations