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

    Neuronpedia

    INDEX
    Explanations

    based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    based
    -2.13
    BASED
    -1.41
    Based
    -1.38
     basée
    -1.22
     baseado
    -1.16
     based
    -1.09
     BASED
    -1.08
     basé
    -1.08
     Based
    -1.05
     basadas
    -0.98
    POSITIVE LOGITS
     free
    0.66
     
    0.64
     extra
    0.64
     special
    0.63
     par
    0.62
     “
    0.60
     full
    0.59
     non
    0.58
     normal
    0.58
     "
    0.57
    Act Density 0.047%

    No Known Activations