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

    Neuronpedia

    INDEX
    Explanations

    Quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Š
    -0.07
     Sto
    -0.07
    .IsNullOr
    -0.07
     craving
    -0.06
     �
    -0.06
     ql
    -0.06
     نفس
    -0.06
    -ни
    -0.06
     รอง
    -0.06
     بن
    -0.06
    POSITIVE LOGITS
     shell
    0.07
     VStack
    0.07
    TEM
    0.07
    ARR
    0.07
    hydration
    0.06
     Your
    0.06
     прес
    0.06
     exec
    0.06
    EXEC
    0.06
    ark
    0.06
    Act Density 0.000%

    No Known Activations