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

    Neuronpedia

    INDEX
    Explanations

    URLs ending in ](

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fog
    0.35
    Fog
    0.32
     Wool
    0.31
     Fog
    0.31
    霧
    0.31
     hous
    0.30
     Seal
    0.30
    ятся
    0.30
    汇
    0.30
    ложен
    0.30
    POSITIVE LOGITS
     ಅಭಿಮಾನ
    0.39
     recombin
    0.37
     préférences
    0.34
    संदर्भ
    0.34
    ’.
    0.34
     deducting
    0.33
     ActionMode
    0.33
    jami
    0.32
     或者
    0.32
     그냥
    0.31
    Act Density 0.005%

    No Known Activations