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

    Neuronpedia

    INDEX
    Explanations

    .compile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uto
    -0.07
    bero
    -0.06
     Dit
    -0.06
     Asia
    -0.06
    ='+
    -0.06
     Sales
    -0.06
     inclusion
    -0.06
    mb
    -0.06
    embros
    -0.06
    ismic
    -0.06
    POSITIVE LOGITS
    �
    0.07
    多少
    0.07
     breached
    0.06
    _pw
    0.06
    lä
    0.06
     ayında
    0.06
    _FM
    0.06
    帮助
    0.06
     coupons
    0.06
    _dept
    0.06
    Act Density 0.001%

    No Known Activations