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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Garland
    -0.07
    _Grid
    -0.07
     Outcome
    -0.07
    _Collections
    -0.07
    -service
    -0.06
    OURCE
    -0.06
    ายน
    -0.06
     همراه
    -0.06
    ]:↵↵
    -0.06
     сут
    -0.06
    POSITIVE LOGITS
     steadily
    0.07
     whim
    0.07
     debts
    0.06
     Crowley
    0.06
     เง
    0.06
     deprived
    0.06
    approved
    0.06
     imageURL
    0.06
     рід
    0.06
     transc
    0.06
    Act Density 0.016%

    No Known Activations