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

    Neuronpedia

    INDEX
    Explanations

    Liberia and "liber-" words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilities
    -0.07
     historians
    -0.07
     Insets
    -0.06
     enchanted
    -0.06
    orgia
    -0.06
    leftrightarrow
    -0.06
     eleven
    -0.06
    čení
    -0.06
     center
    -0.06
    omial
    -0.06
    POSITIVE LOGITS
     stressing
    0.06
     damn
    0.06
     پر
    0.06
    lut
    0.06
    농
    0.06
     Bom
    0.06
    стр
    0.06
    ِر
    0.06
     sağlar
    0.06
     JsonResult
    0.06
    Act Density 0.005%

    No Known Activations