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

    Neuronpedia

    INDEX
    Explanations

    animal welfare and ethics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    স্ক
    0.79
     XMFLOAT
    0.77
     型
    0.75
     கிஷோர்
    0.73
    الث
    0.70
    струк
    0.70
    Liqu
    0.67
     ヘア
    0.67
     హె
    0.66
     depositors
    0.65
    POSITIVE LOGITS
     animal
    2.70
     animals
    2.48
    Animal
    2.46
     Animal
    2.42
    animal
    2.38
     Animals
    2.28
    Animals
    2.23
    动物
    2.23
    動物
    2.21
    animals
    2.21
    Act Density 0.118%

    No Known Activations