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

    Neuronpedia

    INDEX
    Explanations

    technical concepts or abstract ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.49
    0.47
     C
    0.47
     J
    0.47
    a
    0.46
     B
    0.46
     K
    0.46
    Find
    0.45
     Review
    0.44
     L
    0.43
    POSITIVE LOGITS
     eigenfunctions
    0.49
     irritation
    0.49
     isotropy
    0.48
     නිසා
    0.48
     reactance
    0.47
     irrég
    0.47
     energetics
    0.47
     discoloration
    0.46
    operateur
    0.46
     whatnot
    0.46
    Act Density 0.000%

    No Known Activations