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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    였다
    -0.08
    -pencil
    -0.07
    ivial
    -0.07
     ok
    -0.07
     exist
    -0.07
     outsourcing
    -0.07
    .Name
    -0.07
    	lbl
    -0.07
    לר
    -0.07
    xml
    -0.07
    POSITIVE LOGITS
    Mech
    0.06
    Utility
    0.06
     البع
    0.06
    ﱭ
    0.06
    保證
    0.06
     yavaş
    0.06
    كات
    0.06
    כיו
    0.06
     Rapids
    0.06
    ⊣
    0.06
    Act Density 0.040%

    No Known Activations