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

    Neuronpedia

    INDEX
    Explanations

    Mixed code and language snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ਦਾ
    -0.07
     Vir
    -0.07
    /i
    -0.07
    ভ
    -0.07
     respondent
    -0.07
     reader
    -0.07
     limiting
    -0.07
    urve
    -0.07
     resident
    -0.06
     substit
    -0.06
    POSITIVE LOGITS
     hingegen
    0.09
     സംഘ
    0.08
    (es
    0.08
    째
    0.08
     naman
    0.08
     xe
    0.08
    -ż
    0.08
     gigante
    0.08
     Barca
    0.08
     Remaining
    0.08
    Act Density 0.035%

    No Known Activations