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

    Neuronpedia

    INDEX
    Explanations

    Qualified names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spiral
    -0.08
     paramName
    -0.07
    ційного
    -0.07
     양
    -0.07
    ptest
    -0.07
     Văn
    -0.06
     съ
    -0.06
    оличество
    -0.06
    systems
    -0.06
     آغاز
    -0.06
    POSITIVE LOGITS
    APA
    0.07
    FullName
    0.07
    itos
    0.06
    =output
    0.06
     Lansing
    0.06
     UD
    0.06
     Feinstein
    0.06
     drafting
    0.06
     Oakland
    0.06
     fullName
    0.06
    Act Density 0.011%

    No Known Activations