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

    Neuronpedia

    INDEX
    Explanations

    define something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.45
     đình
    1.33
    idated
    1.30
    šit
    1.29
     calendário
    1.27
    ších
    1.25
     to
    1.24
     calendario
    1.22
    ší
    1.20
    に合わせて
    1.18
    POSITIVE LOGITS
    <unused505>
    1.72
    <unused1874>
    1.71
     Hector
    1.71
    <end_of_image>
    1.70
     Vapor
    1.67
     makeSound
    1.67
    req
    1.66
    7
    1.63
     respir
    1.62
     Kohn
    1.60
    Act Density 0.302%

    No Known Activations