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

    Neuronpedia

    INDEX
    Explanations

    Columbian and pre-Columbian eras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bond
    0.74
    ുകൊണ്ട്
    0.72
    ২৬
    0.70
     once
    0.68
     bonds
    0.68
     cropped
    0.66
     Lire
    0.66
     Once
    0.64
    脆弱
    0.64
     "#
    0.64
    POSITIVE LOGITS
    கிர
    0.75
     proton
    0.73
    睬
    0.73
     Jeep
    0.73
    apj
    0.72
    ரி
    0.72
     му
    0.72
    uzz
    0.71
    arında
    0.70
    Whit
    0.70
    Act Density 0.002%

    No Known Activations