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

    Neuronpedia

    INDEX
    Explanations

    when you're / when we're / trying to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     della
    0.48
     emphasised
    0.48
     asserted
    0.47
     tiet
    0.45
     inhibited
    0.45
     intellect
    0.45
     contradicts
    0.45
    咟
    0.45
     delle
    0.44
     winner
    0.44
    POSITIVE LOGITS
    0
    0.64
    ead
    0.46
    item
    0.45
    IM
    0.45
    Est
    0.43
    trials
    0.43
    וג
    0.43
    agles
    0.43
    SS
    0.42
    FL
    0.41
    Act Density 0.002%

    No Known Activations