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

    Neuronpedia

    INDEX
    Explanations

    modal verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    circ
    -0.07
    으
    -0.06
    DataSource
    -0.06
     tip
    -0.06
    _factors
    -0.06
    Activity
    -0.06
    quo
    -0.06
    (return
    -0.06
    Subview
    -0.06
     mümkün
    -0.06
    POSITIVE LOGITS
    \App
    0.07
     isIn
    0.07
    		↵↵
    0.07
     HttpHeaders
    0.07
    ै.↵
    0.07
    _INS
    0.07
    '))↵↵↵
    0.06
     нужно
    0.06
     diligently
    0.06
    	↵	↵↵
    0.06
    Act Density 0.003%

    No Known Activations