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

    Neuronpedia

    INDEX
    Explanations

    options for different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disturbs
    0.38
    回去
    0.37
     inform
    0.36
     establecidas
    0.36
     quote
    0.36
    quote
    0.36
    emails
    0.36
    {
    0.36
     일단
    0.35
    ricanes
    0.35
    POSITIVE LOGITS
    spaceBetween
    0.49
     Heating
    0.43
     نفسها
    0.43
    ό
    0.42
     ப
    0.42
     þis
    0.41
    အောင်
    0.41
     आकृति
    0.41
    hto
    0.39
    ダイニング
    0.39
    Act Density 0.001%

    No Known Activations