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

    Neuronpedia

    INDEX
    Explanations

    everything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Packages
    -0.07
     fontFamily
    -0.06
    一区
    -0.06
    ло
    -0.06
    เกล
    -0.06
     compositions
    -0.06
    струк
    -0.06
    Saudi
    -0.06
    Conflict
    -0.06
     ub
    -0.06
    POSITIVE LOGITS
    ({↵
    0.07
     opens
    0.06
    тен
    0.06
     ETF
    0.06
     GAM
    0.06
    }`,↵
    0.06
     Kim
    0.06
     San
    0.06
     rocked
    0.06
     term
    0.06
    Act Density 0.311%

    No Known Activations