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

    Neuronpedia

    INDEX
    Explanations

    believe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     react
    -0.08
    arsing
    -0.07
    нер
    -0.06
     dojo
    -0.06
    _Act
    -0.06
     Hits
    -0.06
     İng
    -0.06
     EditorGUI
    -0.06
     nichts
    -0.06
    .getState
    -0.06
    POSITIVE LOGITS
     believe
    0.07
    ій
    0.06
    规范
    0.06
    *y
    0.06
    ๆ
    0.06
    coverage
    0.06
     compassionate
    0.06
     Manufacturer
    0.06
     swiftly
    0.06
     Fish
    0.06
    Act Density 0.008%

    No Known Activations