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

    Neuronpedia

    INDEX
    Explanations

    date placeholder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uración
    0.40
     shui
    0.38
    ysl
    0.37
     distillation
    0.36
     pê
    0.36
    ังกฤษ
    0.35
    ⎆
    0.35
    㖅
    0.35
     breasts
    0.34
     Confira
    0.34
    POSITIVE LOGITS
     DATE
    0.63
    DATE
    0.61
     Date
    0.60
    Date
    0.55
     date
    0.54
    日期
    0.54
                                   
    0.50
    date
    0.47
    日付
    0.46
              
    0.45
    Act Density 0.008%

    No Known Activations