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

    Neuronpedia

    INDEX
    Explanations

    changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PLA
    -0.07
     구글
    -0.06
     politics
    -0.06
     flaw
    -0.06
    248
    -0.06
     analý
    -0.06
     Moderator
    -0.06
     exagger
    -0.06
    _datasets
    -0.06
    workspace
    -0.06
    POSITIVE LOGITS
    atypes
    0.07
    (Bit
    0.06
     kingdoms
    0.06
     demise
    0.06
    оне
    0.06
    řád
    0.06
    slu
    0.06
    cling
    0.06
     Apartments
    0.06
    (Il
    0.05
    Act Density 0.015%

    No Known Activations