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

    Neuronpedia

    INDEX
    Explanations

    linear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unos
    -0.06
    SCI
    -0.06
     suppose
    -0.06
    _CODE
    -0.06
     macros
    -0.06
    YP
    -0.06
    nas
    -0.06
     inference
    -0.05
    aku
    -0.05
    ontent
    -0.05
    POSITIVE LOGITS
    lh
    0.08
    peech
    0.08
     Gather
    0.07
    picked
    0.07
    лев
    0.07
     pkg
    0.07
    /year
    0.07
    ��
    0.06
     красив
    0.06
    ійської
    0.06
    Act Density 0.005%

    No Known Activations