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

    Neuronpedia

    INDEX
    Explanations

    example contact information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.49
     City
    0.48
     blog
    0.45
     Unlock
    0.45
     LGBTQ
    0.44
     M
    0.44
     F
    0.44
     HER
    0.44
     vegan
    0.43
     Hen
    0.43
    POSITIVE LOGITS
    Telefon
    0.47
    assurer
    0.45
    Numero
    0.45
    룰
    0.44
    ⸩
    0.43
    します
    0.43
    $=\
    0.43
     ؛
    0.42
    ｨ
    0.42
    ۔
    0.42
    Act Density 0.005%

    No Known Activations