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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kick
    -0.07
    Tam
    -0.07
    province
    -0.07
    ılım
    -0.06
    dál
    -0.06
     проте
    -0.06
    .animate
    -0.06
    tgt
    -0.06
    imiz
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     hasn
    0.06
     UIAlertView
    0.06
     quot
    0.06
    -method
    0.06
    .setdefault
    0.06
     distraction
    0.06
     Mot
    0.06
     May
    0.06
     Master
    0.05
     DS
    0.05
    Act Density 0.001%

    No Known Activations