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

    Neuronpedia

    INDEX
    Explanations

    try...except block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    拒
    0.40
    砟
    0.39
    碛
    0.39
     signalled
    0.38
     стрелецкой
    0.37
     BuildableName
    0.37
     assaulting
    0.37
     मारपीट
    0.37
     signaled
    0.36
    Datasets
    0.36
    POSITIVE LOGITS
     block
    1.38
     blocks
    1.33
     bloc
    1.20
     bloco
    1.20
    块
    1.18
     bloques
    1.15
     ब्लॉक
    1.13
     blok
    1.13
    block
    1.12
     блока
    1.12
    Act Density 0.029%

    No Known Activations