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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caroline
    -0.07
    _to
    -0.07
     nettsteder
    -0.07
     Yue
    -0.06
     storyt
    -0.06
    	RE
    -0.06
     presidente
    -0.06
     nau
    -0.06
     street
    -0.06
     Lost
    -0.06
    POSITIVE LOGITS
    のに
    0.07
    ))]↵
    0.06
    .appspot
    0.06
    �
    0.06
     รวม
    0.06
    求
    0.06
     відповідаль
    0.06
    �
    0.06
    (getString
    0.06
     možné
    0.06
    Act Density 0.016%

    No Known Activations