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

    Neuronpedia

    INDEX
    Explanations

    technical topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSSet
    -0.07
     //////////
    -0.07
    บรร
    -0.07
     ข
    -0.06
     QDateTime
    -0.06
    �
    -0.06
    永
    -0.06
     Waters
    -0.06
    ạp
    -0.06
    �ng
    -0.06
    POSITIVE LOGITS
     DIM
    0.07
    -profit
    0.06
     appointed
    0.06
    nal
    0.06
     Valk
    0.06
    .getSession
    0.06
    	final
    0.06
     fiercely
    0.06
     Hern
    0.06
    ými
    0.06
    Act Density 0.102%

    No Known Activations