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

    Neuronpedia

    INDEX
    Explanations

    more than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Others
    0.44
     itp
    0.42
     др
    0.41
    Especially
    0.39
     Especially
    0.38
    фра
    0.37
    compassing
    0.37
     Others
    0.36
     afar
    0.36
     حقی
    0.36
    POSITIVE LOGITS
     entire
    0.84
     combined
    0.73
    combined
    0.71
    Combined
    0.69
     Combined
    0.66
    entire
    0.65
     Entire
    0.63
    整个
    0.62
     весь
    0.58
     gesamten
    0.58
    Act Density 0.024%

    No Known Activations