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

    Neuronpedia

    INDEX
    Explanations

    disclaims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ambda
    -0.07
    -th
    -0.07
    _Lean
    -0.06
    กราคม
    -0.06
    -co
    -0.06
     سعود
    -0.06
     stutter
    -0.06
     слово
    -0.06
     swearing
    -0.06
     cum
    -0.06
    POSITIVE LOGITS
    _->
    0.07
     harvesting
    0.07
    (cfg
    0.07
     DEFINE
    0.07
     DISCLAIMS
    0.07
     üzerine
    0.06
    onen
    0.06
    ...
    0.06
     lobby
    0.06
    (env
    0.06
    Act Density 0.001%

    No Known Activations