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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λεκ
    -0.07
    Resp
    -0.07
    (SYS
    -0.07
    DSL
    -0.07
     toast
    -0.06
     identification
    -0.06
     massacre
    -0.06
     kinase
    -0.06
     ritual
    -0.06
     Detection
    -0.06
    POSITIVE LOGITS
     Barker
    0.06
    OUNT
    0.06
     خد
    0.06
    cannot
    0.06
     Kavanaugh
    0.06
     eigentlich
    0.06
     زمانی
    0.06
     japanese
    0.06
     COMPLETE
    0.06
    updated
    0.06
    Act Density 0.074%

    No Known Activations