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

    Neuronpedia

    INDEX
    Explanations

    career launch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hmm
    0.42
    athletes
    0.37
     forbind
    0.36
    actions
    0.36
    Compute
    0.36
    path
    0.35
    dashboard
    0.35
    bon
    0.35
    យៈ
    0.35
    clock
    0.35
    POSITIVE LOGITS
     ratione
    0.45
     propre
    0.44
     subject
    0.43
    щен
    0.41
     Examiner
    0.41
    таю
    0.41
     DN
    0.41
     concept
    0.40
     brig
    0.40
     Literatur
    0.40
    Act Density 0.001%

    No Known Activations