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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    719
    -0.07
     Arrival
    -0.07
     Assigned
    -0.07
    uffer
    -0.07
    /K
    -0.07
     Balls
    -0.06
     Öğren
    -0.06
     disob
    -0.06
    KL
    -0.06
    566
    -0.06
    POSITIVE LOGITS
    !";
↵
    0.07
    Owned
    0.07
    Physics
    0.06
    _ctrl
    0.06
     لها
    0.06
    createForm
    0.06
     kred
    0.06
    _FOLDER
    0.06
     сделать
    0.06
    ظˆط
    0.06
    Act Density 0.010%

    No Known Activations