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

    Neuronpedia

    INDEX
    Explanations

    is/it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileWriter
    -0.07
     chảy
    -0.07
     frau
    -0.07
    mine
    -0.06
     Convenient
    -0.06
     Petersburg
    -0.06
     giáo
    -0.06
    �
    -0.06
    石
    -0.06
    题
    -0.06
    POSITIVE LOGITS
     Damen
    0.06
    Member
    0.06
     generals
    0.06
    htag
    0.06
    PostExecute
    0.06
    िकट
    0.06
    адж
    0.06
    Instantiate
    0.06
     congrat
    0.06
    embro
    0.06
    Act Density 0.020%

    No Known Activations