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

    Neuronpedia

    INDEX
    Explanations

    statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AREA
    -0.07
    ，以
    -0.06
     if
    -0.06
    oogle
    -0.06
     cu
    -0.06
    Equivalent
    -0.06
    awesome
    -0.06
     جا
    -0.06
     former
    -0.06
    "When
    -0.06
    POSITIVE LOGITS
     movers
    0.07
    exter
    0.06
     ㅇ
    0.06
     Ngb
    0.06
     riches
    0.06
    xeb
    0.06
    gi
    0.06
    .zeros
    0.06
    ообраз
    0.06
    fte
    0.06
    Act Density 0.077%

    No Known Activations