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

    Neuronpedia

    INDEX
    Explanations

    Joining materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吸毒
    -0.08
    ût
    -0.07
    ROUTE
    -0.07
    ickey
    -0.07
    怦
    -0.07
    屾
    -0.07
     tụ
    -0.07
     accounting
    -0.07
     tumult
    -0.07
    Soon
    -0.06
    POSITIVE LOGITS
    钢厂
    0.07
    ?>">↵
    0.07
     więks
    0.07
    	Token
    0.07
    )::
    0.07
    ;\↵
    0.07
    )==
    0.07
     clones
    0.07
     preorder
    0.07
    0.06
    Act Density 0.030%

    No Known Activations