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

    Neuronpedia

    INDEX
    Explanations

    tutor/tuition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     týden
    -0.07
     روش
    -0.06
    St
    -0.06
     сила
    -0.06
     '|
    -0.06
     DEV
    -0.06
    ۹
    -0.06
    θηκε
    -0.06
     vulnerabilities
    -0.06
    데
    -0.06
    POSITIVE LOGITS
     tuition
    0.09
     khung
    0.08
    axon
    0.07
     needy
    0.07
     Mona
    0.07
     Chu
    0.07
     تغ
    0.07
     Higgins
    0.07
     Knot
    0.06
    (cam
    0.06
    Act Density 0.002%

    No Known Activations