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

    Neuronpedia

    INDEX
    Explanations

    Chinese education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    boor
    0.41
    ಂದ್ರ
    0.40
     devenue
    0.38
    Miscellaneous
    0.38
    厸
    0.38
    OCITY
    0.38
    Louisiana
    0.38
     使っ
    0.38
    ुलकर
    0.37
    istet
    0.37
    POSITIVE LOGITS
     Jimmy
    0.41
     appreciate
    0.40
     appreciation
    0.39
     Sergio
    0.38
    危険
    0.38
     duties
    0.38
     Kontakt
    0.37
     contr
    0.36
     Conta
    0.36
     duty
    0.35
    Act Density 0.000%

    No Known Activations