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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ques
    -0.07
    ates
    -0.06
     exist
    -0.06
    �
    -0.06
    ств
    -0.06
     messages
    -0.06
     tụ
    -0.06
    754
    -0.06
    956
    -0.06
    RV
    -0.06
    POSITIVE LOGITS
     docks
    0.07
    �
    0.06
    출장안마
    0.06
     hacia
    0.06
     bols
    0.06
    .alibaba
    0.06
    .getString
    0.06
     испыт
    0.06
     Bapt
    0.06
     κάθε
    0.06
    Act Density 0.090%

    No Known Activations