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

    Neuronpedia

    INDEX
    Explanations

    verbs related to performing or doing actions

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

    faire, hacer, make

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    garek
    -0.43
    RegressionTest
    -0.42
     desconhe
    -0.42
     gewisser
    -0.41
     Umwel
    -0.41
     bahía
    -0.40
     vété
    -0.40
     pręd
    -0.39
     Pfarr
    -0.39
     sobrevivir
    -0.39
    POSITIVE LOGITS
     make
    1.08
     Make
    1.03
    make
    1.03
     hacen
    0.94
     hacer
    0.93
    makes
    0.92
    Make
    0.92
     Making
    0.91
     Makes
    0.91
    Hacer
    0.90
    Act Density 0.002%

    No Known Activations