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

    Neuronpedia

    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">(
    -0.06
     diversion
    -0.06
     �
    -0.06
     dolls
    -0.06
     Baylor
    -0.06
     society
    -0.05
     Remarks
    -0.05
    istribution
    -0.05
    ﻮ
    -0.05
     přip
    -0.05
    POSITIVE LOGITS
     endTime
    0.08
    _lr
    0.07
    -Agent
    0.07
    明
    0.07
     DAL
    0.07
    =create
    0.07
    _active
    0.06
     augmented
    0.06
     Cornel
    0.06
     customer
    0.06
    Act Density 0.012%

    No Known Activations