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

    Neuronpedia

    INDEX
    Explanations

    always consult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     giurid
    0.41
     ..$
    0.41
     ferram
    0.40
     anty
    0.39
     przepis
    0.39
     ditu
    0.39
     পারেন
    0.38
    推荐
    0.38
    PARTMENT
    0.38
     autoridad
    0.37
    POSITIVE LOGITS
     consult
    1.01
    Consult
    0.96
    consult
    0.95
     Consult
    0.91
     consulted
    0.88
     consultation
    0.86
     CONSULT
    0.86
     Consultation
    0.85
     consultar
    0.82
     consulter
    0.81
    Act Density 0.003%

    No Known Activations