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

    Neuronpedia

    INDEX
    Explanations

    Code/technical questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thảo
    -0.08
    缟
    -0.08
    ='$
    -0.07
    व
    -0.07
     earning
    -0.07
    Verdana
    -0.07
     dependence
    -0.07
    皎
    -0.07
     Child
    -0.07
    פגישה
    -0.07
    POSITIVE LOGITS
    ają
    0.07
    PASS
    0.07
    いくら
    0.07
     코드
    0.07
     hệ
    0.07
     Å
    0.06
     pyplot
    0.06
     PIN
    0.06
    雉
    0.06
     valide
    0.06
    Act Density 0.060%

    No Known Activations