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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     چت
    -0.07
     Cooper
    -0.06
     Morse
    -0.06
    wake
    -0.06
    اذا
    -0.06
     Rooney
    -0.06
     získal
    -0.06
    onet
    -0.06
     contacted
    -0.06
    594
    -0.06
    POSITIVE LOGITS
    (statement
    0.07
     Prel
    0.07
    _reordered
    0.07
    (right
    0.07
     diagonal
    0.06
     complain
    0.06
     complained
    0.06
     avant
    0.06
    简单
    0.06
     vale
    0.06
    Act Density 0.005%

    No Known Activations