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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HOST
    -0.06
    pc
    -0.06
    (mask
    -0.06
    Brains
    -0.06
     dealloc
    -0.06
     Thing
    -0.06
     člán
    -0.06
    _SEG
    -0.06
    χεί
    -0.06
    뮤
    -0.06
    POSITIVE LOGITS
    她
    0.07
    incy
    0.06
    �
    0.06
     Immediately
    0.06
    ventional
    0.06
    到
    0.06
    صه
    0.06
     Tow
    0.06
    ，並
    0.06
     از
    0.06
    Act Density 0.001%

    No Known Activations