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

    Neuronpedia

    INDEX
    Explanations

    AutoLayout, Daily Mail, Virtual Machines, RabbitMQ, Marketing cloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iaal
    -1.70
    Sadly
    -1.65
    Thankfully
    -1.61
    不仅
    -1.55
    toir
    -1.51
    Также
    -1.50
     locura
    -1.48
     maniere
    -1.47
     perceptible
    -1.45
    Warum
    -1.44
    POSITIVE LOGITS
     their
    1.84
     at
    1.70
     in
    1.67
     In
    1.63
     an
    1.60
     before
    1.58
     when
    1.50
     often
    1.50
     had
    1.49
     this
    1.45
    Act Density 0.254%

    No Known Activations