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

    Neuronpedia

    INDEX
    Explanations

    to get to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Linton
    0.44
     Blair
    0.43
     发表
    0.42
     ücretsiz
    0.41
    抿
    0.40
    🤘
    0.40
    smarty
    0.39
     бесплат
    0.39
         
    0.38
    回路
    0.38
    POSITIVE LOGITS
    ry
    0.48
    ફળ
    0.47
     novice
    0.44
    رم
    0.44
    भवती
    0.42
     face
    0.42
    രും
    0.41
    k
    0.40
    hus
    0.40
     punishment
    0.40
    Act Density 0.002%

    No Known Activations