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

    Neuronpedia

    INDEX
    Explanations

    name, entity, greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எனவே
    0.26
    ‚
    0.26
    忧
    0.25
    かなり
    0.25
     பொழுது
    0.24
    यूपी
    0.24
    }^{*}
    0.24
     gosto
    0.24
    }^{*}=
    0.24
    理由は
    0.24
    POSITIVE LOGITS
    isa
    0.32
    name
    0.27
    0.24
    templatemo
    0.24
     aptly
    0.24
     '
    0.24
     Par
    0.23
     Hatch
    0.23
     `
    0.23
     Echo
    0.22
    Act Density 0.327%

    No Known Activations