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

    Neuronpedia

    INDEX
    Explanations

    inflation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canc
    -0.07
    igious
    -0.07
    anc
    -0.06
    _phr
    -0.06
    礼
    -0.06
     Conditions
    -0.06
    ��
    -0.06
    ModelError
    -0.06
     Critical
    -0.06
     TokenType
    -0.06
    POSITIVE LOGITS
    setDescription
    0.07
     používá
    0.07
     compression
    0.07
     efficient
    0.06
     sám
    0.06
    <p
    0.06
    //
↵
    0.06
     pul
    0.06
    				
↵
    0.06
     mushroom
    0.06
    Act Density 0.017%

    No Known Activations