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

    Neuronpedia

    INDEX
    Explanations

    opinions and uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eln
    -0.07
    eil
    -0.06
    ingers
    -0.06
    尖
    -0.06
    Tam
    -0.06
    	v
    -0.06
    帮
    -0.06
    Manip
    -0.06
    DDD
    -0.06
     do
    -0.06
    POSITIVE LOGITS
     compuls
    0.07
     vale
    0.07
     License
    0.07
     DRV
    0.06
    トル
    0.06
     alloy
    0.06
    .pp
    0.06
     cx
    0.06
     Prov
    0.06
    '))↵↵↵
    0.06
    Act Density 0.051%

    No Known Activations