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

    Neuronpedia

    INDEX
    Explanations

    benefits and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apathy
    0.50
     strangely
    0.47
    0.47
     nearly
    0.46
     every
    0.46
     mercury
    0.46
     youthful
    0.45
     sentences
    0.45
     senior
    0.44
     young
    0.44
    POSITIVE LOGITS
    เลือก
    0.50
    itettura
    0.46
    委托
    0.45
    ulières
    0.45
     Gregorio
    0.44
    揆
    0.44
    ल्प
    0.43
    法则
    0.43
    ائدة
    0.43
    借鉴
    0.43
    Act Density 0.001%

    No Known Activations