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

    Neuronpedia

    INDEX
    Explanations

    producer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replay
    -0.06
     Buyer
    -0.06
    ↵                        ↵
    -0.06
     suffix
    -0.06
    [z
    -0.06
    nější
    -0.06
     loving
    -0.05
    _folders
    -0.05
     suction
    -0.05
    auge
    -0.05
    POSITIVE LOGITS
     afs
    0.07
     UserProfile
    0.07
     capitalism
    0.07
     PTSD
    0.07
     resulted
    0.07
    IsRequired
    0.07
     Conserv
    0.07
     vind
    0.07
     Network
    0.06
     clusters
    0.06
    Act Density 0.000%

    No Known Activations