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

    Neuronpedia

    INDEX
    Explanations

    states or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पिछले
    0.51
    לי
    0.49
    נט
    0.47
    爱好者
    0.46
     privind
    0.46
    ете
    0.46
    שי
    0.46
     comportamenti
    0.46
     специфи
    0.45
    ות
    0.44
    POSITIVE LOGITS
     Hôtel
    0.47
     vegetable
    0.47
    field
    0.46
     till
    0.44
     kind
    0.44
     playwright
    0.43
     spacious
    0.43
     आणखी
    0.43
     Festival
    0.43
     Russia
    0.42
    Act Density 0.002%

    No Known Activations