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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сделать
    -0.07
     dow
    -0.07
     Stones
    -0.06
    _impl
    -0.06
    arta
    -0.06
    _Entity
    -0.06
     inch
    -0.06
     scorer
    -0.06
     venom
    -0.06
    .RowStyles
    -0.06
    POSITIVE LOGITS
     Benefits
    0.07
    .required
    0.06
    Amazing
    0.06
    共和国
    0.06
    orElse
    0.06
     benefits
    0.06
     danske
    0.06
    _To
    0.06
     acknow
    0.06
     №
    0.06
    Act Density 0.024%

    No Known Activations