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

    Neuronpedia

    INDEX
    Explanations

    Computer addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     जिल
    -0.08
     opinión
    -0.07
     trivia
    -0.07
    =input
    -0.07
    riott
    -0.07
    иши
    -0.07
    elt
    -0.07
    .input
    -0.07
     जिले
    -0.07
    SERV
    -0.07
    POSITIVE LOGITS
     kemampuan
    0.11
    能力
    0.10
     无限
    0.10
     mampu
    0.10
     limitless
    0.10
     قادر
    0.10
     Capability
    0.10
     Ability
    0.09
     capability
    0.09
    ھن
    0.09
    Act Density 0.005%

    No Known Activations