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

    Neuronpedia

    INDEX
    Explanations

    routing and multi-user targets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    जीलैंड
    0.39
              
    0.39
    zeta
    0.38
    eda
    0.35
    espół
    0.35
     عدم
    0.34
    ச்
    0.34
    imetry
    0.34
     Verkehr
    0.34
    nofollow
    0.34
    POSITIVE LOGITS
     path
    0.70
     путь
    0.61
    path
    0.59
     PATH
    0.54
     pathway
    0.53
    路径
    0.51
     paths
    0.49
     Path
    0.47
    Path
    0.47
     caminho
    0.47
    Act Density 0.000%

    No Known Activations