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

    Neuronpedia

    INDEX
    Explanations

    Git commit hashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ennes
    -0.07
     funkc
    -0.07
     Communist
    -0.07
    kończył
    -0.07
     veh
    -0.07
    军人
    -0.07
     عليك
    -0.07
     tors
    -0.06
     SCHOOL
    -0.06
     conceal
    -0.06
    POSITIVE LOGITS
    停产
    0.07
    Cannot
    0.07
    ราคา
    0.07
    社会资本
    0.07
    פגיעה
    0.07
    \application
    0.07
    ⁄
    0.07
     Notes
    0.07
     mdi
    0.07
    :]
    0.07
    Act Density 0.056%

    No Known Activations