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

    Neuronpedia

    INDEX
    Explanations

    connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seeking
    -0.07
     Workout
    -0.06
     windshield
    -0.06
     mug
    -0.06
     Probe
    -0.06
    _<?
    -0.06
     med
    -0.06
    _armor
    -0.06
    .stats
    -0.06
     centerX
    -0.06
    POSITIVE LOGITS
    ayne
    0.08
    득
    0.07
     comfortably
    0.07
     اظ
    0.06
     wreckage
    0.06
    titre
    0.06
    κ
    0.06
    ochen
    0.06
    ayız
    0.06
     روح
    0.06
    Act Density 0.010%

    No Known Activations