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

    Neuronpedia

    INDEX
    Explanations

    documentation and responsibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    全局
    0.30
     sophistic
    0.30
     considérer
    0.29
    investissement
    0.28
    全球
    0.28
     pobreza
    0.28
     optimale
    0.28
     afirmar
    0.28
     isomorphisms
    0.28
     investir
    0.28
    POSITIVE LOGITS
     troubleshooting
    0.32
     Weekly
    0.32
     daily
    0.30
     weekly
    0.30
     Assist
    0.30
     ежеднев
    0.30
     tweaked
    0.29
     Monitoring
    0.29
     assist
    0.29
     sửa
    0.29
    Act Density 0.121%

    No Known Activations