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

    Neuronpedia

    INDEX
    Explanations

    stall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     здоб
    -0.07
    Replacing
    -0.07
     Dě
    -0.06
    وفي
    -0.06
    Century
    -0.06
    ่งข
    -0.06
    .Logging
    -0.06
    최
    -0.06
    JKLMNOP
    -0.06
    您的
    -0.06
    POSITIVE LOGITS
     fist
    0.07
    attendance
    0.06
    Crud
    0.06
    _DRIVE
    0.06
     jobject
    0.06
    Passwords
    0.06
     anos
    0.06
     sentido
    0.06
     isAuthenticated
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations