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

    Neuronpedia

    INDEX
    Explanations

    adding items or reducing temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HL
    0.45
    HO
    0.43
     schle
    0.42
     kötü
    0.41
     HOPE
    0.41
     glimpses
    0.41
     शुभ
    0.41
    LP
    0.40
     dwóch
    0.40
    残念
    0.40
    POSITIVE LOGITS
    咾
    0.53
     Adds
    0.50
     ώστε
    0.47
    adding
    0.45
    添加
    0.45
     Adding
    0.44
    加热
    0.42
    煅
    0.42
     ))->
    0.41
     వివా
    0.41
    Act Density 0.002%

    No Known Activations