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

    Neuronpedia

    INDEX
    Explanations

    tweets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    暄
    -0.07
     adjustments
    -0.07
    hế
    -0.06
     reminis
    -0.06
    츨
    -0.06
    tees
    -0.06
    MY
    -0.06
    绻
    -0.06
    ᄇ
    -0.06
     aktual
    -0.06
    POSITIVE LOGITS
    }',↵
    0.07
     cidade
    0.07
    _selector
    0.07
    ews
    0.07
     Doug
    0.07
    agenta
    0.06
    (owner
    0.06
    猹
    0.06
    ი
    0.06
    _baseline
    0.06
    Act Density 0.002%

    No Known Activations