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

    Neuronpedia

    INDEX
    Explanations

    linking states and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.53
     които
    0.49
    osaurs
    0.46
     americanos
    0.45
    _
    0.45
     jamás
    0.42
     kteří
    0.41
     zombies
    0.41
     которые
    0.40
     eukaryotes
    0.40
    POSITIVE LOGITS
     underpinned
    0.59
     facilitated
    0.55
     overseen
    0.53
     triggered
    0.51
     fuelled
    0.50
     attributed
    0.50
     accompanied
    0.50
     complemented
    0.49
     enabled
    0.49
    combined
    0.49
    Act Density 0.007%

    No Known Activations