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
     constructions
    -0.07
    幕
    -0.07
    莉
    -0.07
    벨
    -0.07
     inici
    -0.06
     попыт
    -0.06
    람
    -0.06
     karıştır
    -0.06
    .Transfer
    -0.06
     objeto
    -0.06
    POSITIVE LOGITS
     owned
    0.07
    mouth
    0.06
     sind
    0.06
     ABOUT
    0.06
    (prefix
    0.06
    .lin
    0.06
    SignUp
    0.06
    VERTISE
    0.06
    Average
    0.06
    cube
    0.06
    Act Density 0.011%

    No Known Activations