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

    Neuronpedia

    INDEX
    Explanations

    version and format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lenny
    0.42
     despite
    0.42
     Hala
    0.41
    报错
    0.41
      
    0.41
    any
    0.40
    inha
    0.39
     shouldn
    0.39
     kunt
    0.39
     freck
    0.39
    POSITIVE LOGITS
    建設
    0.59
    ство
    0.54
    рия
    0.50
    хар
    0.48
     construir
    0.48
    вач
    0.47
    橋
    0.47
     besonder
    0.46
    龍
    0.45
    茥
    0.45
    Act Density 0.002%

    No Known Activations