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

    Neuronpedia

    INDEX
    Explanations

    technical detail and accessibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     substituted
    0.46
    buttonBar
    0.46
     estudio
    0.45
     letech
    0.45
     charity
    0.45
     nonprofit
    0.45
    cepteur
    0.44
     السنوات
    0.44
    ឆ្នាំ
    0.44
    an
    0.43
    POSITIVE LOGITS
    S
    0.50
    har
    0.49
    ο
    0.49
    U
    0.48
    MP
    0.48
    H
    0.48
    strat
    0.47
    C
    0.47
     strat
    0.47
    D
    0.46
    Act Density 0.004%

    No Known Activations