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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guides
    -0.07
     stir
    -0.07
    LIN
    -0.07
    plug
    -0.06
     ERC
    -0.06
    ANCE
    -0.06
    Lazy
    -0.06
    خی
    -0.06
     addiction
    -0.06
     Identifier
    -0.06
    POSITIVE LOGITS
    ven
    0.06
    _constants
    0.06
    (colors
    0.06
    erge
    0.06
    ###
    0.06
    تمع
    0.06
    ταση
    0.06
    ).↵↵↵↵
    0.06
    .yaml
    0.06
     ]↵↵↵
    0.06
    Act Density 0.110%

    No Known Activations