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

    Neuronpedia

    INDEX
    Explanations

    blog post excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (RE
    -0.06
     hacia
    -0.06
    되었습니다
    -0.06
    BagConstraints
    -0.06
    _re
    -0.06
     cerc
    -0.06
    -за
    -0.06
     compr
    -0.06
     cupid
    -0.06
    larından
    -0.06
    POSITIVE LOGITS
    _WIFI
    0.08
    283
    0.08
     servings
    0.07
     traveling
    0.07
    CLASS
    0.07
     Holden
    0.07
     KC
    0.07
    35
    0.07
    547
    0.07
    22
    0.07
    Act Density 0.012%

    No Known Activations