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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Zip
    -0.07
     تغ
    -0.07
     charset
    -0.07
    apphire
    -0.06
     найти
    -0.06
     pairing
    -0.06
     features
    -0.06
    	 ↵
    -0.06
     bağ
    -0.06
    peat
    -0.06
    POSITIVE LOGITS
    스
    0.07
    类型
    0.07
    confirm
    0.06
     Mr
    0.06
    EDIATE
    0.06
    ΗΣ
    0.06
    manager
    0.06
     forwarded
    0.06
     Permanent
    0.06
     every
    0.06
    Act Density 0.070%

    No Known Activations