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

    Neuronpedia

    INDEX
    Explanations

    oping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    額
    -0.07
    (String
    -0.07
    _inst
    -0.07
     islands
    -0.06
    ign
    -0.06
    로서
    -0.06
    ριος
    -0.06
     หล
    -0.06
    :"#
    -0.06
     Become
    -0.06
    POSITIVE LOGITS
    fred
    0.07
    рів
    0.07
     PDF
    0.06
    处
    0.06
     pleased
    0.06
    tensorflow
    0.06
    adder
    0.06
    .arch
    0.06
    éc
    0.06
     steroid
    0.06
    Act Density 0.006%

    No Known Activations