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

    Neuronpedia

    INDEX
    Explanations

    Kanji characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ることができる
    1.51
    つまり
    1.49
    𝓗
    1.39
    ることができます
    1.38
    utuskan
    1.37
    すなわち
    1.36
    1.33
    ዉ
    1.30
     एवरीवन
    1.29
    ipple
    1.27
    POSITIVE LOGITS
     fum
    1.18
     hate
    1.12
     woe
    1.12
    únior
    1.07
     lotus
    1.06
     bloom
    1.05
    кор
    1.05
     gis
    1.04
     contrast
    1.03
     flood
    1.03
    Act Density 0.000%

    No Known Activations