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

    Neuronpedia

    INDEX
    Explanations

    Florence, Italy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
            
    1.80
    re
    1.64
    ية
    1.63
    א
    1.59
    n
    1.59
     आपल्या
    1.52
    uct
    1.51
    ist
    1.49
        
    1.48
    tains
    1.47
    POSITIVE LOGITS
    ﻜ
    1.67
    AM
    1.55
     inscreve
    1.55
    eers
    1.55
    )(
    1.52
    КА
    1.52
    ﻼ
    1.48
    עת
    1.45
    ﻄ
    1.45
    )}=
    1.45
    Act Density 0.001%

    No Known Activations