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

    Neuronpedia

    INDEX
    Explanations

    Blueprint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fac
    -0.08
     Susan
    -0.08
     Souls
    -0.07
     pessoa
    -0.07
     مسئله
    -0.07
     آنچه
    -0.07
     embarrassment
    -0.07
     cosas
    -0.07
    arc
    -0.07
    iji
    -0.07
    POSITIVE LOGITS
     Blueprint
    0.11
     blueprint
    0.11
    Blueprint
    0.07
    complexType
    0.07
     underground
    0.07
    prints
    0.06
     blackout
    0.06
     الت
    0.06
     بول
    0.06
    utter
    0.06
    Act Density 0.001%

    No Known Activations