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

    Neuronpedia

    INDEX
    Explanations

    python import Auto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হয়
    0.38
    hspace
    0.37
     설명
    0.37
    秵
    0.36
    κο
    0.35
     ==
    0.35
    ίν
    0.35
    Simpl
    0.35
     descon
    0.35
     libert
    0.35
    POSITIVE LOGITS
     Vector
    0.40
     vector
    0.39
    ський
    0.38
     register
    0.38
     wearable
    0.37
    hstack
    0.36
     Oracle
    0.36
     Registered
    0.36
     UI
    0.35
     Router
    0.35
    Act Density 0.004%

    No Known Activations