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

    Neuronpedia

    INDEX
    Explanations

    build, provide, sliced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    туга
    0.46
    рд
    0.45
     trifling
    0.45
     oscillate
    0.45
     Фурга
    0.43
    <unused555>
    0.42
     precarious
    0.42
    CLionProjects
    0.42
     පිළිබ
    0.40
    :])
    0.39
    POSITIVE LOGITS
     alleles
    0.48
    Vo
    0.45
     chief
    0.44
    Id
    0.44
    稹
    0.43
     Chief
    0.43
     nouns
    0.42
     Ha
    0.42
     Vo
    0.42
     Immediate
    0.42
    Act Density 0.000%

    No Known Activations