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

    Neuronpedia

    INDEX
    Explanations

    uby

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     client
    -0.07
     combineReducers
    -0.06
     sorter
    -0.06
     '@
    -0.06
    LM
    -0.06
     fenced
    -0.06
    نى
    -0.06
     етап
    -0.06
    经理
    -0.06
    地区
    -0.06
    POSITIVE LOGITS
     bothers
    0.07
     mismatch
    0.06
     EVERY
    0.06
     Stephen
    0.06
     feel
    0.06
    (validation
    0.06
    -rest
    0.06
    (link
    0.06
     Logging
    0.06
    modification
    0.06
    Act Density 0.001%

    No Known Activations