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

    Neuronpedia

    INDEX
    Explanations

    after its wrap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̞
    0.76
    Accessories
    0.64
    utils
    0.64
     accessory
    0.63
     Accessory
    0.63
    ంగా
    0.63
    accessories
    0.63
     themselves
    0.62
    ึ
    0.62
    osto
    0.62
    POSITIVE LOGITS
     κάνει
    0.81
     dijo
    0.79
     Percy
    0.78
     said
    0.76
     მან
    0.76
     manages
    0.75
     zegt
    0.75
     compd
    0.73
     opposes
    0.73
    foldername
    0.73
    Act Density 0.000%

    No Known Activations