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

    Neuronpedia

    INDEX
    Explanations

    code or foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maları
    -0.08
     wszyst
    -0.07
     Might
    -0.06
     프랑스
    -0.06
    }",
    -0.06
     Duch
    -0.06
     Girls
    -0.06
    -clock
    -0.06
    852
    -0.06
     Testing
    -0.06
    POSITIVE LOGITS
    van
    0.22
    avan
    0.17
    ivan
    0.13
    ovan
    0.13
    ван
    0.11
    vanized
    0.10
    AN
    0.10
    vana
    0.09
     vant
    0.09
     Donovan
    0.09
    Act Density 0.016%

    No Known Activations