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

    Neuronpedia

    INDEX
    Explanations

    experiments and analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lr
    -0.08
     WORD
    -0.07
    Як
    -0.07
    footer
    -0.07
     KT
    -0.06
    Progress
    -0.06
    Junior
    -0.06
    lerde
    -0.06
     H
    -0.06
    ','%
    -0.06
    POSITIVE LOGITS
    �
    0.07
    设施
    0.07
     trop
    0.06
    itan
    0.06
    ูรณ
    0.06
    ันธ
    0.06
    MainActivity
    0.06
    (dd
    0.06
     wifi
    0.06
     unitOfWork
    0.06
    Act Density 0.096%

    No Known Activations