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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agua
    -0.06
    �
    -0.06
    ателей
    -0.06
    obre
    -0.06
    _Command
    -0.06
    خاص
    -0.06
    eru
    -0.05
    ущ
    -0.05
     cosine
    -0.05
     thoát
    -0.05
    POSITIVE LOGITS
     Dame
    0.08
    ,True
    0.07
    751
    0.07
     TOO
    0.07
     REMOVE
    0.07
     implies
    0.06
     stylish
    0.06
     parti
    0.06
     und
    0.06
    TECTED
    0.06
    Act Density 0.000%

    No Known Activations