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

    Neuronpedia

    INDEX
    Explanations

    already exists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BUFF
    -0.07
    ventory
    -0.06
     sin
    -0.06
    困
    -0.06
    [position
    -0.06
     franch
    -0.06
    codes
    -0.06
     immunity
    -0.06
     Spe
    -0.06
     penalty
    -0.06
    POSITIVE LOGITS
     zaháj
    0.07
    _LAYER
    0.07
     gebru
    0.06
    .shopping
    0.06
    _BLOCK
    0.06
     EZ
    0.06
     zm
    0.06
     existed
    0.06
     이를
    0.06
     vergi
    0.06
    Act Density 0.010%

    No Known Activations