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

    Neuronpedia

    INDEX
    Explanations

    arbitration, arbitrage, arbit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toned
    -0.07
     фото
    -0.07
    Dates
    -0.06
     ):↵↵
    -0.06
     зазнач
    -0.06
     incomes
    -0.06
     traversal
    -0.06
    Treatment
    -0.06
     cultivated
    -0.06
     darker
    -0.06
    POSITIVE LOGITS
     Claim
    0.07
     arbit
    0.07
    ��
    0.07
    sequences
    0.07
    ((__
    0.07
    aptor
    0.06
    RESET
    0.06
    sphere
    0.06
     vypad
    0.06
    force
    0.06
    Act Density 0.003%

    No Known Activations