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

    Neuronpedia

    INDEX
    Explanations

    quietly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mortality
    -0.06
     hijo
    -0.06
     onBind
    -0.06
    .hash
    -0.06
     колич
    -0.06
     weapons
    -0.06
    Prop
    -0.06
     sempre
    -0.06
     Sole
    -0.06
     mq
    -0.06
    POSITIVE LOGITS
     Byz
    0.06
    鲁
    0.06
     Exiting
    0.06
    caller
    0.06
     사라
    0.06
     misguided
    0.06
     rogue
    0.06
    ckt
    0.06
    )i
    0.06
    Suite
    0.06
    Act Density 0.011%

    No Known Activations