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

    Neuronpedia

    INDEX
    Explanations

    Dialogue / conversational fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Promo
    -0.07
    lexport
    -0.06
    apiro
    -0.06
    -di
    -0.06
    стре
    -0.06
    206
    -0.06
     Penguin
    -0.06
    etails
    -0.06
     собі
    -0.06
    orts
    -0.06
    POSITIVE LOGITS
     compensation
    0.07
    .setTime
    0.07
    ")↵
    0.07
    loops
    0.07
    <char
    0.07
     عنوان
    0.07
    wie
    0.06
    setText
    0.06
     compensate
    0.06
     screwed
    0.06
    Act Density 0.027%

    No Known Activations