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

    Neuronpedia

    INDEX
    Explanations

    seeking information or opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱽ
    1.23
    τέρα
    1.09
    έ
    1.07
    ра
    1.06
    торы
    1.05
    دت
    1.05
    ﺱ
    1.05
    时期
    1.05
    氲
    1.02
    amsmath
    1.00
    POSITIVE LOGITS
     solace
    1.09
     reassurance
    1.07
     refuge
    1.06
     revenge
    1.02
     redress
    0.99
    iot
    0.98
     Ż
    0.97
     nuovi
    0.97
     new
    0.94
    }$
    0.92
    Act Density 0.028%

    No Known Activations