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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -free
    -0.07
     comida
    -0.06
     Spoon
    -0.06
    ý
    -0.06
     muchos
    -0.06
    _boxes
    -0.06
     aloud
    -0.06
    vtk
    -0.06
     Planning
    -0.06
     неск
    -0.06
    POSITIVE LOGITS
     have
    0.10
     had
    0.09
    ’ve
    0.09
     has
    0.09
    've
    0.09
     Have
    0.08
     Has
    0.08
     jwt
    0.07
     Had
    0.07
    WithType
    0.07
    Act Density 0.035%

    No Known Activations