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

    Neuronpedia

    INDEX
    Explanations

    qualify/disqualify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firewall
    0.58
    DVR
    0.55
     probed
    0.53
    墺
    0.53
     thaw
    0.51
     bunker
    0.50
     goodbye
    0.49
    {
    0.49
     cabinets
    0.48
     teens
    0.48
    POSITIVE LOGITS
     оюн
    0.55
    орга
    0.52
     plupart
    0.50
     Rotating
    0.50
    Rotating
    0.50
    ेन
    0.49
    เร
    0.49
     Pancake
    0.49
     ঠাকুরের
    0.49
     undoubt
    0.49
    Act Density 0.000%

    No Known Activations