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

    Neuronpedia

    INDEX
    Explanations

    _replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，↵
    -0.06
    _problem
    -0.06
     monstrous
    -0.06
     NPCs
    -0.06
     правило
    -0.06
     explos
    -0.06
    роничес
    -0.06
     Gods
    -0.06
    moment
    -0.06
     Paladin
    -0.06
    POSITIVE LOGITS
    _replace
    0.12
     ايران
    0.07
    
    0.07
    ated
    0.07
    (numero
    0.06
     repealed
    0.06
     pesquisa
    0.06
     Dedicated
    0.06
    _guid
    0.06
     {});↵↵
    0.06
    Act Density 0.001%

    No Known Activations