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

    Neuronpedia

    INDEX
    Explanations

    effective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adding
    -0.08
    一行
    -0.07
    rod
    -0.07
    SendMessage
    -0.07
    胡
    -0.07
    	color
    -0.07
    失落
    -0.07
     boat
    -0.06
    ansom
    -0.06
    .Msg
    -0.06
    POSITIVE LOGITS
     effectively
    0.08
    .checked
    0.07
    >';
↵
    0.07
     téc
    0.07
    interest
    0.07
     effectiveness
    0.07
     effective
    0.07
     scare
    0.07
     реак
    0.07
     kä
    0.07
    Act Density 0.039%

    No Known Activations