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

    Neuronpedia

    INDEX
    Explanations

    KeyPair, forEach, speech, Branch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Floyd
    0.44
    wm
    0.38
     Kobe
    0.37
     meanwhile
    0.37
     Essen
    0.37
     Sul
    0.37
    use
    0.37
     Cob
    0.36
    ujem
    0.36
    Cogn
    0.36
    POSITIVE LOGITS
    ಡುವ
    0.40
     dout
    0.39
     배치
    0.39
     pursue
    0.38
     سؤال
    0.38
    ანა
    0.38
     beagle
    0.38
     questions
    0.38
     question
    0.38
     tingkat
    0.38
    Act Density 0.000%

    No Known Activations