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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Desktop
    -0.07
    last
    -0.07
     underrated
    -0.07
     decades
    -0.07
    -google
    -0.06
     ıs
    -0.06
     ruin
    -0.06
     століття
    -0.06
     originate
    -0.06
     SRC
    -0.06
    POSITIVE LOGITS
     Aph
    0.07
     Já
    0.07
     patches
    0.06
    лаб
    0.06
     ]↵
    0.06
    jax
    0.06
    ΕΧ
    0.06
    رب
    0.06
    anguage
    0.06
    險
    0.06
    Act Density 0.005%

    No Known Activations