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

    Neuronpedia

    INDEX
    Explanations

    nor followed by something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    1.27
    ни
    1.25
    ()
    1.11
    :
    1.05
    ม
    0.99
    ，
    0.96
    ی
    0.95
    م
    0.95
    э
    0.95
    很
    0.94
    POSITIVE LOGITS
    もら
    0.94
    ও
    0.93
    ilk
    0.86
    inha
    0.83
    villa
    0.81
    ید
    0.81
    vär
    0.81
     in
    0.80
    rup
    0.79
    も
    0.78
    Act Density 0.002%

    No Known Activations