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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ne
    -0.07
    ância
    -0.07
    ói
    -0.06
    lic
    -0.06
    operate
    -0.06
    -cent
    -0.06
    ıl
    -0.06
    ısıyla
    -0.06
     Rece
    -0.06
    ently
    -0.06
    POSITIVE LOGITS
     (;
    0.06
    Bitcoin
    0.06
     "\""
    0.06
     Schiff
    0.06
     shift
    0.06
    
    0.06
     certificate
    0.06
    .Translate
    0.06
     DataType
    0.06
     zou
    0.06
    Act Density 0.001%

    No Known Activations