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

    Neuronpedia

    INDEX
    Explanations

    compute shared secret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बिर
    0.43
     adhesions
    0.42
     observado
    0.42
     解説
    0.41
    .[[
    0.41
    ികിത്സ
    0.40
    Karo
    0.40
     棉
    0.40
    MTAB
    0.39
    digos
    0.39
    POSITIVE LOGITS
     Deploy
    0.48
     Native
    0.48
     With
    0.46
     Deployment
    0.45
     Task
    0.44
     grew
    0.44
     Match
    0.42
     Employee
    0.42
     주로
    0.42
     Mostly
    0.42
    Act Density 0.001%

    No Known Activations