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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CAM
    -0.07
    男
    -0.06
     TableView
    -0.06
     pedigree
    -0.06
    _MAG
    -0.06
     стра
    -0.06
     理
    -0.06
     foil
    -0.06
    ﾍ
    -0.06
    值
    -0.06
    POSITIVE LOGITS
    říd
    0.07
    ^.
    0.07
    örü
    0.06
    _business
    0.06
     gard
    0.06
    invoke
    0.06
    ژه
    0.06
    	ds
    0.06
    recision
    0.06
     autop
    0.06
    Act Density 0.063%

    No Known Activations