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

    Neuronpedia

    INDEX
    Explanations

    block patterns, spatial layouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्टो
    0.44
     включает
    0.42
     곳
    0.41
     INCLUDE
    0.39
    ８
    0.39
    ９
    0.39
     Lonely
    0.38
    懈
    0.38
     அடை
    0.38
    Ꮩ
    0.38
    POSITIVE LOGITS
     bounds
    0.40
     workloads
    0.38
     bior
    0.38
    Logs
    0.38
    subsec
    0.38
    fak
    0.37
     replication
    0.37
     margins
    0.37
     logs
    0.37
    وين
    0.37
    Act Density 0.000%

    No Known Activations