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

    Neuronpedia

    INDEX
    Explanations

    types of AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بیداری
    0.36
     joueurs
    0.36
     ikon
    0.36
     životu
    0.35
     হাস্য
    0.35
    खास्त
    0.34
     salido
    0.34
    िशनर
    0.34
    らを
    0.34
    嬠
    0.34
    POSITIVE LOGITS
    ======
    0.38
    Benef
    0.37
    <0xE6>
    0.36
    Dex
    0.34
    Ethan
    0.34
    PDA
    0.34
    An
    0.33
    Lin
    0.33
    亜
    0.33
    द
    0.33
    Act Density 0.002%

    No Known Activations