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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reserve
    0.46
    Next
    0.46
    였습니다
    0.46
    matis
    0.46
    mē
    0.45
    makt
    0.44
    umus
    0.44
     интегри
    0.44
    Your
    0.44
    estra
    0.43
    POSITIVE LOGITS
     शिवाय
    0.46
     Neck
    0.45
    ﻉ
    0.45
     centers
    0.43
     Centers
    0.43
     charities
    0.43
     pennies
    0.42
     період
    0.42
     centaines
    0.42
     templates
    0.42
    Act Density 0.000%

    No Known Activations