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

    Neuronpedia

    INDEX
    Explanations

    Possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avaliações
    -0.08
     anzeigen
    -0.08
    襫
    -0.07
    .setView
    -0.07
    镞
    -0.07
     inventions
    -0.07
    🧵
    -0.07
    .Sound
    -0.06
     intolerance
    -0.06
    ☦
    -0.06
    POSITIVE LOGITS
    .My
    0.08
     Program
    0.07
    館
    0.07
     Laugh
    0.07
     Jacobs
    0.07
     subway
    0.07
     Kill
    0.06
    Program
    0.06
     الشهر
    0.06
    ennis
    0.06
    Act Density 0.071%

    No Known Activations