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

    Neuronpedia

    INDEX
    Explanations

    collaborate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uelle
    -0.07
    =en
    -0.07
     mornings
    -0.07
     ast
    -0.07
    فز
    -0.07
    ش
    -0.07
     moo
    -0.07
     Frem
    -0.07
    rost
    -0.06
    EST
    -0.06
    POSITIVE LOGITS
     cwd
    0.07
     technically
    0.07
     popularity
    0.07
    ꧈
    0.07
    isbn
    0.06
     jpg
    0.06
    .github
    0.06
     acknowledged
    0.06
     expans
    0.06
    .ExecuteScalar
    0.06
    Act Density 0.014%

    No Known Activations