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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Execution
    -0.07
    lastic
    -0.07
     состоит
    -0.07
    าสตร
    -0.06
    -looking
    -0.06
    (Display
    -0.06
     lucrative
    -0.06
     отсутств
    -0.06
     jeopard
    -0.06
     RULE
    -0.06
    POSITIVE LOGITS
     eternity
    0.07
    }/>
    0.07
     karıştır
    0.06
     순간
    0.06
     Chennai
    0.06
     ██
    0.06
     }},↵
    0.06
    Zh
    0.06
    *******/↵↵
    0.06
    ruh
    0.06
    Act Density 0.259%

    No Known Activations