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

    Neuronpedia

    INDEX
    Explanations

    Fred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaking
    -0.07
     示
    -0.07
     Show
    -0.07
    。当
    -0.07
    #ae
    -0.07
    Painter
    -0.06
     mould
    -0.06
     questioning
    -0.06
    .Activity
    -0.06
     поз
    -0.06
    POSITIVE LOGITS
     Freder
    0.07
     EDGE
    0.07
    uter
    0.06
    350
    0.06
    �
    0.06
    prefer
    0.06
     Friedrich
    0.06
     робота
    0.06
    684
    0.06
    rodu
    0.06
    Act Density 0.018%

    No Known Activations