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

    Neuronpedia

    INDEX
    Explanations

    imagine how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Costco
    -0.07
    Eu
    -0.07
    Including
    -0.06
    ěle
    -0.06
    afari
    -0.06
    .tests
    -0.06
    نگی
    -0.06
     čt
    -0.06
     použí
    -0.06
    ł
    -0.06
    POSITIVE LOGITS
    _so
    0.07
    (jLabel
    0.07
    ocomplete
    0.06
     �
    0.06
     controversial
    0.06
    QUERY
    0.06
    _pot
    0.06
     Tabs
    0.06
    ）的
    0.06
     brilliant
    0.06
    Act Density 0.023%

    No Known Activations