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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surely
    -0.07
     Kou
    -0.07
     goodbye
    -0.06
     umb
    -0.06
    /email
    -0.06
     silenced
    -0.06
    こん
    -0.06
     litres
    -0.06
     notre
    -0.06
    ，這
    -0.06
    POSITIVE LOGITS
    +C
    0.07
    oldem
    0.07
    +N
    0.06
    ект
    0.06
    ๊
    0.06
     shredd
    0.06
    ẩy
    0.06
    dfunding
    0.06
    <f
    0.06
    \Events
    0.06
    Act Density 0.042%

    No Known Activations