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

    Neuronpedia

    INDEX
    Explanations

    Community

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wine
    -0.06
    oxide
    -0.06
    ]:↵↵
    -0.06
    Now
    -0.06
    '))↵↵
    -0.06
    _letter
    -0.06
    `
↵
    -0.06
    SMTP
    -0.06
     Proposed
    -0.06
     Suitable
    -0.06
    POSITIVE LOGITS
     fled
    0.07
    град
    0.07
    jing
    0.06
     Sơn
    0.06
     Buenos
    0.06
     Jerusalem
    0.06
     تلویزیون
    0.06
     มหาว
    0.06
     etkin
    0.06
    .getFloat
    0.06
    Act Density 0.216%

    No Known Activations