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

    Neuronpedia

    INDEX
    Explanations

    code/coordinates/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erin
    -0.07
     société
    -0.07
    jumlah
    -0.06
     decrypted
    -0.06
     علوم
    -0.06
     best
    -0.06
    สาว
    -0.06
     society
    -0.06
    TypeName
    -0.06
     commonplace
    -0.06
    POSITIVE LOGITS
    』↵↵
    0.07
     hitter
    0.07
     Him
    0.07
    呀
    0.06
    reon
    0.06
    aunch
    0.06
    }*/↵↵
    0.06
    graph
    0.06
    ें।
    0.06
    viewport
    0.06
    Act Density 0.006%

    No Known Activations