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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capacities
    -0.07
     mph
    -0.07
    團
    -0.06
    _dicts
    -0.06
     ecology
    -0.06
    ат
    -0.06
     refugee
    -0.06
    �除
    -0.06
    "encoding
    -0.06
    кат
    -0.06
    POSITIVE LOGITS
    arme
    0.06
    .omg
    0.06
    –
    0.06
    ờ
    0.06
     dorsal
    0.06
    �
    0.06
     sabot
    0.06
     listened
    0.06
     Outer
    0.06
     срав
    0.06
    Act Density 0.033%

    No Known Activations