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

    Neuronpedia

    INDEX
    Explanations

    Effort and reward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icolon
    -0.07
    agogue
    -0.07
     Jou
    -0.06
     produto
    -0.06
     monitored
    -0.06
     elm
    -0.06
     veh
    -0.06
     Slovakia
    -0.06
    cycle
    -0.06
    ズ
    -0.06
    POSITIVE LOGITS
    aaaa
    0.07
    Lv
    0.06
    ked
    0.06
    ActiveSheet
    0.06
    /md
    0.06
    เช
    0.06
    pagesize
    0.06
    responseData
    0.06
     isAuthenticated
    0.06
    animate
    0.06
    Act Density 0.280%

    No Known Activations