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

    Neuronpedia

    INDEX
    Explanations

    code library imports and setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preliquidacion
    0.41
    ney
    0.40
    ăţ
    0.40
     сложных
    0.40
    adayo
    0.39
    ร่างกาย
    0.38
    unez
    0.37
    ariyam
    0.37
    }">${
    0.37
     thisTrial
    0.37
    POSITIVE LOGITS
     Helps
    0.54
     allowing
    0.54
     enables
    0.53
     Enable
    0.53
     Enables
    0.53
     enabling
    0.53
     Add
    0.52
     plugin
    0.52
     allows
    0.51
     plugins
    0.51
    Act Density 0.148%

    No Known Activations