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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جهان
    -0.07
    cctor
    -0.07
    ementia
    -0.06
     thoughtful
    -0.06
    ustain
    -0.06
     Assass
    -0.06
    jvu
    -0.06
     Evan
    -0.06
     Assange
    -0.06
    섭
    -0.06
    POSITIVE LOGITS
     oku
    0.07
     farms
    0.06
    421
    0.06
    (bool
    0.06
    ]
↵
    0.06
    �试
    0.06
    }`↵
    0.06
     conf
    0.06
    ========↵
    0.06
    }↵
    0.06
    Act Density 0.000%

    No Known Activations