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

    Neuronpedia

    INDEX
    Explanations

    language and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ǎi
    0.43
    তো
    0.40
     almo
    0.40
    simile
    0.39
    វា
    0.39
     собира
    0.39
    lava
    0.39
    avorites
    0.39
     teorema
    0.38
     आसपास
    0.38
    POSITIVE LOGITS
    راج
    0.44
    NEUTRON
    0.40
    ດ້ານ
    0.39
     Musicians
    0.39
    AndView
    0.38
     కళ
    0.37
    钎
    0.37
    日本人
    0.36
    าระ
    0.36
     fallen
    0.36
    Act Density 0.003%

    No Known Activations