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

    Neuronpedia

    INDEX
    Explanations

    Figure references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Γ
    -0.07
     Besch
    -0.07
     contrad
    -0.07
    뵨
    -0.07
     מלא
    -0.07
     BST
    -0.07
    	sign
    -0.07
     جاء
    -0.06
     Stra
    -0.06
     Bert
    -0.06
    POSITIVE LOGITS
    成熟的
    0.07
    氮
    0.07
    ETHER
    0.07
    Od
    0.07
    产业基地
    0.07
    ionage
    0.07
     tubing
    0.07
     imageNamed
    0.07
    -centered
    0.07
    uating
    0.07
    Act Density 0.001%

    No Known Activations