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

    Neuronpedia

    INDEX
    Explanations

    confirm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     West
    -0.09
    West
    -0.08
     Xia
    -0.07
     Vel
    -0.07
     DES
    -0.06
    aversal
    -0.06
     WIDTH
    -0.06
     Mah
    -0.06
     Mutable
    -0.06
    逸
    -0.06
    POSITIVE LOGITS
     confirm
    0.15
     confirmed
    0.15
     confirming
    0.14
     confirmation
    0.12
     confirms
    0.11
     Confirm
    0.11
     confirmPassword
    0.10
    confirm
    0.10
    Confirm
    0.10
    confirmed
    0.10
    Act Density 0.011%

    No Known Activations