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

    Neuronpedia

    INDEX
    Explanations

    balancing/equalizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    免费
    -0.06
    flu
    -0.06
    "';
    -0.06
     currentState
    -0.06
    Seen
    -0.06
     vốn
    -0.06
    ###############################################################################↵
    -0.06
    应该
    -0.06
    Outer
    -0.06
    治
    -0.05
    POSITIVE LOGITS
    詳細
    0.07
     publik
    0.06
     poet
    0.06
     Madrid
    0.06
     Cortex
    0.06
     росій
    0.06
    ROWS
    0.06
    Charlie
    0.06
     Indian
    0.06
    IA
    0.06
    Act Density 0.010%

    No Known Activations