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

    Neuronpedia

    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bureaucr
    -0.06
     blah
    -0.06
    фи
    -0.06
     αρχ
    -0.06
    ţ
    -0.06
     traversal
    -0.06
     plush
    -0.05
    یت
    -0.05
     mist
    -0.05
     chant
    -0.05
    POSITIVE LOGITS
    erras
    0.07
    .ClientSize
    0.06
    ieder
    0.06
     twenties
    0.06
    eldon
    0.06
    awy
    0.06
    ียรต
    0.06
    んど
    0.06
    lope
    0.06
    งก
    0.06
    Act Density 0.329%

    No Known Activations