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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gallon
    -0.07
     rare
    -0.07
    くな
    -0.06
    +A
    -0.06
    .Read
    -0.06
    favor
    -0.06
    확
    -0.06
    Luc
    -0.06
     slew
    -0.06
     Rare
    -0.06
    POSITIVE LOGITS
     Uploaded
    0.07
     orn
    0.07
     českých
    0.06
    MainFrame
    0.06
    ัณฑ
    0.06
    由
    0.06
     Ensemble
    0.06
     đ
    0.06
     schop
    0.06
    essed
    0.06
    Act Density 0.015%

    No Known Activations