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

    Neuronpedia

    INDEX
    Explanations

    questions about purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dien
    0.64
    tasks
    0.54
    kania
    0.53
    dn
    0.53
    ud
    0.52
    ib
    0.52
    bst
    0.52
    signatures
    0.52
    macos
    0.52
    re
    0.51
    POSITIVE LOGITS
    撐
    0.50
    ﻪ
    0.49
     Schweiz
    0.48
     nedostat
    0.47
    矇
    0.47
    0.47
     England
    0.45
     সুরে
    0.45
    爛
    0.45
    AH
    0.45
    Act Density 0.000%

    No Known Activations